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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @email
    -0.08
    Prin
    -0.08
     usw
    -0.07
     atmosphere
    -0.07
     Pr
    -0.07
    <|reserved_200016|>
    -0.07
    igts
    -0.07
    ,min
    -0.07
    }@
    -0.07
    _pr
    -0.07
    POSITIVE LOGITS
     tilante
    0.09
     situaties
    0.09
     лин
    0.09
     linear
    0.08
     situazione
    0.08
     לינ
    0.08
     cobrança
    0.08
    វិ
    0.08
     상황
    0.08
     পরিস্থিত
    0.08
    Act Density 0.028%

    No Known Activations