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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yeme
    -0.08
    ži
    -0.06
     {...
    -0.06
     lider
    -0.06
    177
    -0.06
     mockMvc
    -0.06
    kan
    -0.06
     vatandaş
    -0.06
     ':
    -0.06
     hanya
    -0.06
    POSITIVE LOGITS
    _walk
    0.07
     Percent
    0.07
     Rays
    0.07
    Percent
    0.07
    Border
    0.07
     Progress
    0.06
     thirds
    0.06
     Cit
    0.06
    _glob
    0.06
     втра
    0.06
    Act Density 0.005%

    No Known Activations