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

    Neuronpedia

    INDEX
    Explanations

    jacket before someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ismo
    0.96
    니
    0.88
    Stu
    0.86
    Shuffle
    0.83
    Rho
    0.82
    말
    0.82
    ശാസ്ത്ര
    0.81
    ha
    0.81
    ᐢ
    0.80
    ண
    0.80
    POSITIVE LOGITS
    ский
    0.89
    umus
    0.87
     beraten
    0.83
     когато
    0.80
    ovjek
    0.80
     relevantes
    0.77
     względu
    0.76
     understandably
    0.74
     tenang
    0.74
     telepon
    0.73
    Act Density 0.000%

    No Known Activations