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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiếng
    -0.06
     slap
    -0.06
    kaz
    -0.06
     momentum
    -0.06
     Stop
    -0.06
     mejor
    -0.06
     cab
    -0.06
    .We
    -0.06
    channels
    -0.05
     Česk
    -0.05
    POSITIVE LOGITS
    0.07
    _time
    0.07
    атків
    0.07
     смог
    0.07
    _BUF
    0.06
    .slf
    0.06
    Importer
    0.06
    0.06
     Chili
    0.06
    -compose
    0.06
    Act Density 0.000%

    No Known Activations