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

    Neuronpedia

    INDEX
    Explanations

    code structure and multilingual elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ગ્ર
    0.38
    UEL
    0.37
    ิ
    0.37
     যথা
    0.37
    fv
    0.37
    OTH
    0.36
    Greeting
    0.36
    bolo
    0.36
    Codigo
    0.36
    auction
    0.36
    POSITIVE LOGITS
     want
    0.47
     try
    0.44
     pierde
    0.42
     podem
    0.41
     mungkin
    0.40
     pode
    0.40
     somehow
    0.39
     qualcosa
    0.39
     peut
    0.38
     possiamo
    0.38
    Act Density 0.131%

    No Known Activations