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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting nuances in text

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

    ending statements with otherwise or unless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.64
    UserScript
    -0.56
     Signalez
    -0.56
    awtextra
    -0.54
     Walkover
    -0.50
    Jîn
    -0.49
    ɵɵ
    -0.49
     setEmail
    -0.48
    posedge
    -0.48
    DMETHOD
    -0.47
    POSITIVE LOGITS
    ⮕
    0.51
     Económica
    0.47
     Italij
    0.47
     Unterschied
    0.46
     Hälfte
    0.45
     posibilidad
    0.45
     tierras
    0.43
     libertad
    0.43
     either
    0.42
     cosas
    0.42
    Act Density 0.094%

    No Known Activations