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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     önlem
    -0.07
    ạc
    -0.07
    Ignoring
    -0.07
    척
    -0.06
    \models
    -0.06
    مح
    -0.06
    consider
    -0.06
     pursuing
    -0.06
    -parser
    -0.06
    팀
    -0.06
    POSITIVE LOGITS
     –
    0.07
     الي
    0.07
     ；
    0.06
    ').'</
    0.06
    977
    0.06
     :
    0.06
    ?↵
    0.06
     ___
    0.06
     toDate
    0.06
    —
    0.06
    Act Density 0.006%

    No Known Activations