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

    Neuronpedia

    INDEX
    Explanations

    static, fantasy, traditional, partnership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    놁
    0.54
    锜
    0.54
     ismi
    0.51
    zący
    0.49
    Gauche
    0.48
    鹦
    0.48
    எல்
    0.48
     galima
    0.46
    naam
    0.46
    メガ
    0.45
    POSITIVE LOGITS
     first
    0.51
     lieu
    0.50
     role
    0.48
    ние
    0.47
    arno
    0.46
     part
    0.46
     proximate
    0.46
     modo
    0.45
     debt
    0.44
     ray
    0.44
    Act Density 0.000%

    No Known Activations