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

    Neuronpedia

    INDEX
    Explanations

    false otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    これも
    0.38
    arah
    0.37
     enormes
    0.37
     lượng
    0.37
     একজনকে
    0.37
    PHEN
    0.36
    ణ
    0.36
    출
    0.35
    STER
    0.34
    फार
    0.34
    POSITIVE LOGITS
     otherwise
    1.36
     Otherwise
    1.34
    otherwise
    1.26
    Otherwise
    1.23
     OTHERWISE
    1.17
    否则
    1.13
     그렇지
    1.08
     अन्यथा
    1.02
    sonsten
    0.99
     Else
    0.94
    Act Density 0.019%

    No Known Activations