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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forced
    -0.07
    ös
    -0.07
    escape
    -0.06
    *******/↵
    -0.06
     jurisdictions
    -0.06
     modules
    -0.06
     sagt
    -0.06
    n
    -0.06
    nesc
    -0.06
    試
    -0.06
    POSITIVE LOGITS
     bài
    0.07
     aria
    0.06
    	false
    0.06
     cutter
    0.06
     unimagin
    0.06
    inner
    0.06
    accuracy
    0.06
    lášení
    0.06
    .hash
    0.06
    Seleccione
    0.06
    Act Density 0.003%

    No Known Activations