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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .receiver
    -0.07
     Với
    -0.07
     bans
    -0.07
    _raw
    -0.07
    .state
    -0.06
     noted
    -0.06
    .Enc
    -0.06
    iks
    -0.06
    .Dataset
    -0.06
    .AF
    -0.06
    POSITIVE LOGITS
    esco
    0.06
     twins
    0.06
    alytics
    0.06
    .ones
    0.06
    _Index
    0.06
     deducted
    0.06
     společnosti
    0.06
     detox
    0.06
    olare
    0.06
     Fot
    0.06
    Act Density 0.008%

    No Known Activations