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

    Neuronpedia

    INDEX
    Explanations

    Okay, model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acus
    0.44
     Imm
    0.41
     देऊ
    0.41
    markets
    0.40
    葳
    0.40
     Atención
    0.40
     অচ
    0.39
     त्व
    0.39
     Acer
    0.38
     Ac
    0.38
    POSITIVE LOGITS
    Think
    0.41
    ônica
    0.40
    尊敬
    0.38
     불편
    0.38
    дума
    0.38
     tyrosine
    0.37
    Davies
    0.37
     unint
    0.37
    yta
    0.36
    ونها
    0.36
    Act Density 0.000%

    No Known Activations