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

    Neuronpedia

    INDEX
    Explanations

    advocate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    advoc
    -1.13
     voice
    -1.01
     advocate
    -1.01
    Advoc
    -0.97
    Negoti
    -0.96
     Advocates
    -0.96
     Negoti
    -0.93
     advocated
    -0.93
     voix
    -0.92
    Advocate
    -0.92
    POSITIVE LOGITS
    ,
    0.56
     import
    0.52
     on
    0.52
     and
    0.51
    boon
    0.50
    pick
    0.49
     that
    0.48
     index
    0.47
     the
    0.47
     for
    0.47
    Act Density 0.052%

    No Known Activations