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

    Neuronpedia

    INDEX
    Explanations

    words related to remembering or forgetting

    oai_token-act-pair · gemini-2.0-flash

    forget

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.77
    sizeCache
    -0.75
    MessageOf
    -0.72
     kasarigan
    -0.67
     OFDb
    -0.64
    fromnode
    -0.64
    Tikang
    -0.62
    Tazama
    -0.60
    LookAnd
    -0.59
     Himo
    -0.59
    POSITIVE LOGITS
     they
    0.53
     about
    0.50
     we
    0.46
     jSON
    0.46
    ichio
    0.46
     that
    0.44
    зион
    0.43
     paramInt
    0.42
     ta
    0.42
    carril
    0.42
    Act Density 1.249%

    No Known Activations