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

    Neuronpedia

    INDEX
    Explanations

    annual events and years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _reg
    -0.07
    _show
    -0.07
    nom
    -0.06
    Percent
    -0.06
     month
    -0.06
    37
    -0.06
    メラ
    -0.06
    ीकरण
    -0.06
    distance
    -0.06
     Husband
    -0.06
    POSITIVE LOGITS
     Troll
    0.07
     gz
    0.07
    _lua
    0.07
    .readline
    0.07
     almond
    0.06
     nokt
    0.06
     làn
    0.06
    _hosts
    0.06
     ***!↵
    0.06
     trolls
    0.06
    Act Density 0.242%

    No Known Activations