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

    Neuronpedia

    INDEX
    Explanations

    Code and data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     garments
    -0.07
    _decor
    -0.06
     palm
    -0.06
     improve
    -0.06
    济
    -0.06
     colored
    -0.06
     Keller
    -0.06
    transforms
    -0.06
     инструмент
    -0.06
    presso
    -0.06
    POSITIVE LOGITS
    _email
    0.07
    .Disabled
    0.06
     spiel
    0.06
    *);↵↵
    0.06
    \System
    0.06
     wz
    0.06
    ₀
    0.06
     grop
    0.06
     "\(
    0.06
     goof
    0.06
    Act Density 0.023%

    No Known Activations