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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิเศษ
    -0.07
     Seas
    -0.07
    .normal
    -0.06
     consectetur
    -0.06
     seas
    -0.06
     obstruction
    -0.06
     monday
    -0.06
     rov
    -0.06
    _den
    -0.06
    ществ
    -0.06
    POSITIVE LOGITS
    (userData
    0.07
    Clean
    0.07
    .Itoa
    0.07
    latable
    0.07
     €
    0.07
     $"
    0.07
     $
    0.06
    earable
    0.06
    )data
    0.06
    ArrayType
    0.06
    Act Density 0.005%

    No Known Activations