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

    Neuronpedia

    INDEX
    Explanations

    conjunctions/separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าส
    -0.07
    кова
    -0.07
    дн
    -0.07
    -trans
    -0.06
    Ru
    -0.06
     프리
    -0.06
     indign
    -0.06
    Notify
    -0.06
    gh
    -0.06
    _Show
    -0.06
    POSITIVE LOGITS
    (username
    0.06
     hall
    0.06
     Ac
    0.06
    activate
    0.06
    нитель
    0.06
    ophage
    0.06
    稍
    0.06
    <br
    0.06
    ***
    0.06
     pob
    0.06
    Act Density 0.026%

    No Known Activations