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

    Neuronpedia

    INDEX
    Explanations

    something else or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ))
    0.35
    lg
    0.32
    प्
    0.30
    なっている
    0.30
     आहेत
    0.30
    itone
    0.29
    )|
    0.29
     Vogt
    0.29
     interchangeably
    0.29
    )
    0.29
    POSITIVE LOGITS
     else
    0.84
    Else
    0.66
     Else
    0.63
    else
    0.56
     ELSE
    0.54
     different
    0.50
     akin
    0.49
    ELSE
    0.46
     farklı
    0.46
     khác
    0.46
    Act Density 0.035%

    No Known Activations