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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -flight
    -0.07
     spinal
    -0.07
     accum
    -0.07
    Normal
    -0.06
    rana
    -0.06
     defa
    -0.06
     صاح
    -0.06
    ्गत
    -0.06
     knack
    -0.06
     출시
    -0.06
    POSITIVE LOGITS
    ливість
    0.07
    CHEDULE
    0.07
     Kraj
    0.07
     implode
    0.06
    ToStr
    0.06
     -----------------------------------------------------------------------------↵
    0.06
    变
    0.06
    로서
    0.06
    duğunu
    0.06
    healthy
    0.06
    Act Density 0.006%

    No Known Activations