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

    Neuronpedia

    INDEX
    Explanations

    Science publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wł
    -0.07
     cal
    -0.07
    -tm
    -0.07
     않을
    -0.07
     נתונים
    -0.07
     Arabia
    -0.07
    udio
    -0.07
    _palette
    -0.07
    თ
    -0.07
    ประธาน
    -0.07
    POSITIVE LOGITS
     accelerated
    0.07
     taper
    0.07
     consistently
    0.07
    ➽
    0.07
     Select
    0.07
     Searching
    0.07
    successfully
    0.07
    fst
    0.06
    涠
    0.06
    ers
    0.06
    Act Density 0.007%

    No Known Activations