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

    Neuronpedia

    INDEX
    Explanations

    _crossentropy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     яка
    -0.07
    ुम
    -0.07
    ्बर
    -0.06
    fwrite
    -0.06
     PMC
    -0.06
     Interaction
    -0.06
    _fix
    -0.06
     객체
    -0.06
    spa
    -0.06
     범
    -0.06
    POSITIVE LOGITS
    _crossentropy
    0.08
     clo
    0.07
     Dave
    0.06
    ительным
    0.06
    _factory
    0.06
    сі
    0.06
     Strategy
    0.06
    vents
    0.06
    Orders
    0.06
    (completion
    0.06
    Act Density 0.001%

    No Known Activations