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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pages
    -0.07
     arcs
    -0.07
    (columns
    -0.06
    .assertNull
    -0.06
     IRS
    -0.06
    _ca
    -0.06
    城市
    -0.06
    ecure
    -0.06
    _prev
    -0.06
    .Inf
    -0.06
    POSITIVE LOGITS
    ように
    0.07
     �
    0.06
     aller
    0.06
     feat
    0.06
    �
    0.06
    -property
    0.06
    experimental
    0.06
     Chrysler
    0.06
    累
    0.06
    (delta
    0.06
    Act Density 0.004%

    No Known Activations