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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ющей
    -0.06
     scrutiny
    -0.06
    .:.:.:
    -0.06
    เต
    -0.06
    니아
    -0.06
    severity
    -0.06
    оне
    -0.06
     malzem
    -0.06
    _Manager
    -0.06
     systematic
    -0.06
    POSITIVE LOGITS
     -->↵
    0.09
     shard
    0.07
    ++++++++++++++++++++++++++++++++
    0.06
     Sears
    0.06
    /auth
    0.06
    	sb
    0.06
    _CONN
    0.06
     Rebel
    0.06
     greatest
    0.06
     proves
    0.06
    Act Density 0.289%

    No Known Activations