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

    Neuronpedia

    INDEX
    Explanations

    swift function and variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    厓
    0.44
    ("|"+"
    0.42
     cương
    0.41
    Fran
    0.41
    Gert
    0.40
     রাস
    0.40
    RELATIVA
    0.40
     божомолдору
    0.39
     школова
    0.39
    วิ่ง
    0.39
    POSITIVE LOGITS
     var
    1.03
    var
    1.00
     func
    0.98
    func
    0.95
     let
    0.79
    let
    0.77
     Var
    0.70
    Var
    0.66
     VAR
    0.63
    Func
    0.61
    Act Density 0.011%

    No Known Activations