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

    Neuronpedia

    INDEX
    Explanations

    Greek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Career
    -0.08
    Career
    -0.07
     career
    -0.07
    preci
    -0.07
    다가
    -0.06
     Julia
    -0.06
     disturbing
    -0.06
     Edward
    -0.06
    =all
    -0.06
     Abel
    -0.06
    POSITIVE LOGITS
    Greek
    0.10
     Greek
    0.10
     Athens
    0.10
     Greeks
    0.07
    �
    0.07
    _Parms
    0.07
     Greece
    0.07
    ?>:</
    0.07
    achs
    0.07
    latable
    0.06
    Act Density 0.008%

    No Known Activations