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

    Neuronpedia

    INDEX
    Explanations

    resource

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -hooks
    -0.07
    /send
    -0.06
    +j
    -0.06
    cht
    -0.06
    [m
    -0.06
     cv
    -0.06
    _closed
    -0.06
    _bet
    -0.06
     Hag
    -0.06
    ذر
    -0.06
    POSITIVE LOGITS
     resource
    0.07
     wasting
    0.07
    lei
    0.07
    ervative
    0.06
    对于
    0.06
    Slides
    0.06
    �
    0.06
     могу
    0.06
    imest
    0.06
     wrestlers
    0.06
    Act Density 0.007%

    No Known Activations