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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پیشینه
    -0.07
     머
    -0.07
     Working
    -0.07
     Aid
    -0.07
    นใจ
    -0.07
     Ski
    -0.07
    ocations
    -0.07
    hait
    -0.07
     jets
    -0.07
     chars
    -0.06
    POSITIVE LOGITS
     edin
    0.07
     대한
    0.06
     खतर
    0.06
     vrij
    0.06
     strokeLine
    0.06
    น
    0.06
     eup
    0.06
    �
    0.06
    ruc
    0.05
    /ml
    0.05
    Act Density 0.018%

    No Known Activations