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

    Neuronpedia

    INDEX
    Explanations

    crisis hotline numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.70
    i
    0.56
     bifur
    0.53
    ن
    0.52
    inę
    0.50
    inien
    0.50
     telefone
    0.49
    ती
    0.49
     telepon
    0.49
    रानी
    0.48
    POSITIVE LOGITS
    ة
    0.63
    માં
    0.54
    ünüz
    0.49
    ية
    0.47
    ének
    0.47
    ING
    0.46
    ಪಡ
    0.46
    լ
    0.46
    íč
    0.46
    ونات
    0.45
    Act Density 0.146%

    No Known Activations