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

    Neuronpedia

    INDEX
    Explanations

    sentences regarding what someone will do or what is going to happen in the future

    oai_token-act-pair · gemini-2.0-flash

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awaiter
    -0.56
    ldb
    -0.46
    scriptcase
    -0.46
    __((
    -0.45
    nonatomic
    -0.44
     utafitiHapana
    -0.43
    rungsseite
    -0.43
     MainAxisSize
    -0.43
    complexType
    -0.42
    lant
    -0.42
    POSITIVE LOGITS
    contentLoaded
    0.74
    writeFieldEnd
    0.74
     ویکی‌پدی
    0.74
     sèche
    0.70
     Савезне
    0.67
     Tapia
    0.59
    intios
    0.59
    Celebrating
    0.58
     ainfi
    0.58
     Celebrating
    0.58
    Act Density 0.792%

    No Known Activations