Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    forms and requests related to legal and official documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text on forms or handwritten notes

    np_acts-logits-general · gemini-2.0-flash

    handwritten notes, marks, or notations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.85
    +:+
    -0.82
    offsetof
    -0.81
     متعلقه
    -0.80
     kasarigan
    -0.80
    UnsafeEnabled
    -0.78
     estimés
    -0.77
    NUMX
    -0.76
    IntoConstraints
    -0.72
    ftagPool
    -0.72
    POSITIVE LOGITS
     photocopy
    0.63
     feuille
    0.59
     pencil
    0.56
     handwritten
    0.56
     marked
    0.54
     sheet
    0.49
     tare
    0.49
     notes
    0.49
     mark
    0.49
     каранда
    0.48
    Act Density 0.354%

    No Known Activations