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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Params
    -0.06
    ='.$
    -0.06
     Lunch
    -0.06
    agement
    -0.06
    كال
    -0.06
     싸
    -0.06
     Rich
    -0.06
     Ash
    -0.06
    Publisher
    -0.05
     Torrent
    -0.05
    POSITIVE LOGITS
    082
    0.07
    .sd
    0.07
     CSR
    0.07
    .STATUS
    0.06
     gcc
    0.06
    assessment
    0.06
    itzerland
    0.06
     �
    0.06
     trainer
    0.06
    _false
    0.06
    Act Density 0.008%

    No Known Activations