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

    Neuronpedia

    INDEX
    Explanations

    -trained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moment
    -0.07
    kovi
    -0.06
    ři
    -0.06
    род
    -0.06
    ôt
    -0.06
     mest
    -0.06
    iteit
    -0.06
     fakt
    -0.06
     explorer
    -0.06
    _qual
    -0.06
    POSITIVE LOGITS
     pretrained
    0.09
    stantiateViewController
    0.07
    .TRAILING
    0.07
    ,...
    0.07
    ..
    0.06
    ....
    0.06
    willReturn
    0.06
    health
    0.06
     peel
    0.06
     water
    0.06
    Act Density 0.004%

    No Known Activations