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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ĕ
    -0.07
    惕
    -0.07
    ߪ
    -0.07
    ﯟ
    -0.07
    ｨ
    -0.07
    SimpleName
    -0.07
    ᆯ
    -0.07
    (effect
    -0.07
    olding
    -0.07
     reflection
    -0.07
    POSITIVE LOGITS
    required
    0.07
    رياض
    0.07
    逝
    0.07
     sarcast
    0.07
     personals
    0.07
    مكان
    0.07
     stan
    0.07
     arsen
    0.07
    حار
    0.07
     distort
    0.07
    Act Density 0.029%

    No Known Activations