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

    Neuronpedia

    INDEX
    Explanations

    authentication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hidden
    -0.07
    requency
    -0.07
    隐藏
    -0.07
    -switch
    -0.07
     judge
    -0.06
     navigating
    -0.06
     sauna
    -0.06
    _books
    -0.06
     nose
    -0.06
     Neural
    -0.06
    POSITIVE LOGITS
     Ag
    0.06
    >P
    0.06
     replicas
    0.06
    Spacing
    0.06
     anch
    0.06
     malaysia
    0.06
     precedence
    0.06
     QU
    0.06
     piv
    0.05
    ,...
    0.05
    Act Density 0.014%

    No Known Activations