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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     출
    0.78
     出
    0.78
     afferm
    0.75
     vyd
    0.74
     divinity
    0.73
    n
    0.73
     아
    0.73
     అస
    0.71
    ਛ
    0.71
    righteous
    0.70
    POSITIVE LOGITS
    Var
    0.88
     Var
    0.85
     var
    0.83
     Potter
    0.76
    var
    0.73
     Stefano
    0.69
    აგ
    0.69
    可以用
    0.68
    itated
    0.68
     Eugenia
    0.67
    Act Density 0.000%

    No Known Activations