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

    Neuronpedia

    INDEX
    Explanations

    appearing and disappearing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一般
    -0.07
    (game
    -0.07
    Hours
    -0.07
    ','
    -0.06
     `
    -0.06
    .TEXT
    -0.06
     ['
    -0.06
     Я
    -0.06
     Sundays
    -0.06
    iled
    -0.06
    POSITIVE LOGITS
     IService
    0.08
     Bain
    0.07
     DEAL
    0.06
     Bengals
    0.06
     Heating
    0.06
    _softc
    0.06
    PU
    0.06
    Kir
    0.06
    arser
    0.06
     Draco
    0.06
    Act Density 0.214%

    No Known Activations