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

    Neuronpedia

    INDEX
    Explanations

    special characters indicating the start or continuation of code sections

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.78
     utafitiHapana
    -0.74
     betweenstory
    -0.69
    Хьажоргаш
    -0.63
    IntoConstraints
    -0.57
    RegressionTest
    -0.56
    EDEFAULT
    -0.56
    -0.56
     kasarigan
    -0.56
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
    ScopeManager
    0.47
     additional
    0.38
     suela
    0.37
    findpost
    0.37
     нале
    0.35
     opening
    0.35
     
    0.35
    uchen
    0.35
     suggested
    0.34
     mante
    0.34
    Act Density 0.000%

    No Known Activations