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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .gov
    -0.07
     midway
    -0.07
    (N
    -0.07
     -$
    -0.07
     fc
    -0.06
    ([(
    -0.06
    салон
    -0.06
     Energ
    -0.06
     Rex
    -0.06
     modulo
    -0.06
    POSITIVE LOGITS
     Supporting
    0.07
    ycling
    0.07
    _poll
    0.07
     Pistol
    0.07
     dest
    0.07
    loth
    0.07
    Checks
    0.06
    _UNLOCK
    0.06
    武装
    0.06
     underlying
    0.06
    Act Density 0.029%

    No Known Activations