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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пись
    -0.07
    istes
    -0.07
    624
    -0.07
     منت
    -0.07
    297
    -0.07
    277
    -0.07
     sms
    -0.06
    kernel
    -0.06
     sus
    -0.06
    мо
    -0.06
    POSITIVE LOGITS
     fileName
    0.07
     можливість
    0.06
    iterator
    0.06
     animateWithDuration
    0.06
    acerb
    0.06
    َج
    0.06
    DIRECT
    0.06
    IGHT
    0.06
    _framework
    0.06
     indirectly
    0.05
    Act Density 0.001%

    No Known Activations