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

    Neuronpedia

    INDEX
    Explanations

    Association

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    略
    -0.08
     entropy
    -0.07
    _Grid
    -0.06
     layers
    -0.06
     bytes
    -0.06
    IR
    -0.06
     fend
    -0.06
    78
    -0.06
    67
    -0.06
     smr
    -0.06
    POSITIVE LOGITS
     Association
    0.19
    Association
    0.12
     association
    0.10
     Assoc
    0.09
     Alliance
    0.09
     Associations
    0.08
    datas
    0.08
    Claims
    0.08
     attract
    0.07
     associations
    0.07
    Act Density 0.009%

    No Known Activations