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

    Neuronpedia

    INDEX
    Explanations

    shape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     合
    -0.06
     돈
    -0.06
    Clip
    -0.06
     twenty
    -0.06
     kurul
    -0.06
     Charles
    -0.06
    τησε
    -0.06
    両
    -0.06
     toward
    -0.06
     samen
    -0.06
    POSITIVE LOGITS
    }-{
    0.07
     robbed
    0.06
    just
    0.06
    _del
    0.06
     gün
    0.06
    Engineering
    0.06
     jav
    0.06
    Cream
    0.06
    almart
    0.06
    owego
    0.06
    Act Density 0.169%

    No Known Activations