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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    টল
    0.82
    }}_{\
    0.81
     warships
    0.80
     tinct
    0.79
    sided
    0.78
    াইভ
    0.77
     minimalistic
    0.77
    emic
    0.76
    𝖗
    0.76
    খিক
    0.76
    POSITIVE LOGITS
    Ener
    0.73
     這個
    0.71
     Га
    0.70
     Gett
    0.70
    س
    0.69
     quiero
    0.66
    Stefan
    0.66
     може
    0.66
    న
    0.66
    മല
    0.65
    Act Density 0.001%

    No Known Activations