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

    Neuronpedia

    INDEX
    Explanations

    Ca

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     android
    -0.07
     anger
    -0.06
    完
    -0.06
    _OVERRIDE
    -0.06
    diff
    -0.06
    01
    -0.06
     vars
    -0.06
    hardware
    -0.06
    ROM
    -0.06
     jars
    -0.06
    POSITIVE LOGITS
    ımın
    0.06
     Cec
    0.06
     thừa
    0.06
    -temp
    0.06
     folly
    0.06
    _effects
    0.06
    unker
    0.06
     час
    0.06
     ilk
    0.06
     côté
    0.06
    Act Density 0.006%

    No Known Activations