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

    Neuronpedia

    INDEX
    Explanations

    Google

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hear
    -0.06
     novels
    -0.06
     Wii
    -0.06
     finished
    -0.06
     detection
    -0.06
    igte
    -0.06
     थ
    -0.06
     praž
    -0.06
     nfs
    -0.06
    (buffer
    -0.06
    POSITIVE LOGITS
     battling
    0.07
     каль
    0.07
    .Dep
    0.06
     वर
    0.06
    oug
    0.06
     –↵↵
    0.06
    ://{
    0.06
     maturity
    0.06
     nerve
    0.06
    asad
    0.06
    Act Density 0.003%

    No Known Activations