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

    Neuronpedia

    INDEX
    Explanations

    Linear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linear
    -1.07
     Linear
    -0.92
    Linear
    -0.92
     David
    -0.88
    linear
    -0.88
     sweet
    -0.73
    David
    -0.73
     Sweet
    -0.68
    sweet
    -0.64
     LINEAR
    -0.64
    POSITIVE LOGITS
     nahilalakip
    0.98
    riwal
    0.94
    RectangleBorder
    0.94
    __(/*!
    0.84
    دانشنامهٔ
    0.84
    KommentareTeilen
    0.84
    ly
    0.83
     Majefty
    0.82
    Бахар
    0.81
    mybatisplus
    0.81
    Act Density 1.335%

    No Known Activations