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

    Neuronpedia

    INDEX
    Explanations

    code file paths and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bathing
    0.40
    ならでは
    0.40
     bathing
    0.38
     shoreline
    0.38
     allele
    0.36
     wavenumber
    0.36
    bills
    0.36
     axe
    0.35
     waven
    0.35
     bathe
    0.34
    POSITIVE LOGITS
    ：“
    0.49
    ："
    0.42
    :"
    0.42
    ：
    0.42
    :”
    0.41
    :...
    0.41
     :"
    0.40
     Какие
    0.40
     وقال
    0.38
    ():
    0.38
    Act Density 0.002%

    No Known Activations