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

    Neuronpedia

    INDEX
    Explanations

    downloading files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Match
    -0.07
    adapt
    -0.07
    ены
    -0.07
    Analyzer
    -0.07
    istas
    -0.07
    .Clone
    -0.07
    Doug
    -0.06
    Sports
    -0.06
    ीग
    -0.06
    sters
    -0.06
    POSITIVE LOGITS
     освещ
    0.07
     говорит
    0.07
    .classes
    0.06
     قادر
    0.06
     SUR
    0.06
     Eğer
    0.06
    0.06
     effective
    0.06
     hypers
    0.06
     sadece
    0.06
    Act Density 0.056%

    No Known Activations