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

    Neuronpedia

    INDEX
    Explanations

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     others
    0.63
     cả
    0.55
    3
    0.54
    Third
    0.54
    Refresh
    0.51
     each
    0.51
    Others
    0.50
     Others
    0.50
    Each
    0.50
     saf
    0.49
    POSITIVE LOGITS
    iliency
    0.61
    astia
    0.59
     Infatti
    0.58
    𝙍
    0.58
    ämme
    0.57
    ಕ
    0.57
    álogo
    0.56
    যজ্ঞ
    0.56
    щаться
    0.55
    rante
    0.55
    Act Density 0.090%

    No Known Activations