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

    Neuronpedia

    INDEX
    Explanations

    AS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (boolean
    -0.08
    オスス
    -0.07
     offensive
    -0.07
     Resolve
    -0.07
    等问题
    -0.07
    .ReadInt
    -0.07
     match
    -0.07
    <HashMap
    -0.07
    HEN
    -0.07
    ることが
    -0.06
    POSITIVE LOGITS
    ปลาย
    0.07
    seeing
    0.07
     waterfall
    0.06
    _every
    0.06
    genre
    0.06
     backing
    0.06
    	yield
    0.06
     citations
    0.06
     decking
    0.06
     Lenin
    0.06
    Act Density 0.001%

    No Known Activations