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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilebilir
    -0.07
    hledem
    -0.06
     pam
    -0.06
    izione
    -0.06
    -sdk
    -0.06
     paed
    -0.06
     residuals
    -0.06
     nalez
    -0.06
    pis
    -0.06
     mw
    -0.06
    POSITIVE LOGITS
    }");↵↵
    0.07
     requiring
    0.07
    ?>/
    0.07
    '")↵
    0.07
     radiation
    0.06
    _native
    0.06
     detention
    0.06
    	I
    0.06
     Evaluation
    0.06
    ohn
    0.06
    Act Density 0.000%

    No Known Activations