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

    Neuronpedia

    INDEX
    Explanations

    favorite color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    can
    0.55
    ه
    0.48
    کان
    0.48
     can
    0.47
    hada
    0.47
    engage
    0.46
     desea
    0.45
    Want
    0.45
     pagos
    0.43
    ocalyptic
    0.43
    POSITIVE LOGITS
     చి
    0.44
     flor
    0.43
    тельностью
    0.42
     ου
    0.42
     culinary
    0.40
     ultraviolet
    0.40
     Sier
    0.40
    ချင်း
    0.39
     Ă
    0.38
     Gourmet
    0.38
    Act Density 0.001%

    No Known Activations