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

    Neuronpedia

    INDEX
    Explanations

    the word "thing" and words associated with an idea or concept

    oai_token-act-pair · gemini-2.0-flash

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.99
    execSQL
    -0.81
     '\\;'
    -0.77
     itſelf
    -0.75
     raiſ
    -0.73
     الحره
    -0.73
     anſ
    -0.69
    WritableDatabase
    -0.69
    __":
    -0.68
    __':
    -0.68
    POSITIVE LOGITS
     intptr
    0.57
     Chwiliwch
    0.56
    TagMode
    0.52
     surla
    0.52
    providedIn
    0.51
     ("
    0.50
     (
    0.50
    IMPORTED
    0.50
     (“
    0.48
     cherchés
    0.48
    Act Density 0.902%

    No Known Activations