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

    Neuronpedia

    INDEX
    Explanations

    Chemical units/compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Helper
    -0.07
    ="{{
    -0.07
     hasher
    -0.07
    {{
    -0.06
    $val
    -0.06
    (IO
    -0.06
    (',');↵
    -0.06
    ��
    -0.06
    {},↵
    -0.06
    뭏
    -0.06
    POSITIVE LOGITS
     superf
    0.09
    -split
    0.08
    olia
    0.08
     fName
    0.07
     bloodstream
    0.07
     Lynch
    0.07
    期待
    0.07
    ocities
    0.07
    pers
    0.07
     rhythm
    0.07
    Act Density 0.016%

    No Known Activations