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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Font
    -0.07
     params
    -0.07
    .path
    -0.07
     data
    -0.07
     boiled
    -0.07
     hel
    -0.06
     mse
    -0.06
     bible
    -0.06
     shortage
    -0.06
     pepper
    -0.06
    POSITIVE LOGITS
     Türk
    0.07
    奧
    0.06
     COMM
    0.06
    ンティ
    0.06
     ((*
    0.06
    rito
    0.06
    одав
    0.06
    Про
    0.06
    \/\/
    0.06
     roadmap
    0.06
    Act Density 0.004%

    No Known Activations