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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vulnerabilities
    -0.06
     legislators
    -0.06
    quake
    -0.06
     confusing
    -0.06
    isin
    -0.06
    ıt
    -0.06
    �
    -0.06
    ournals
    -0.06
    host
    -0.06
     selbst
    -0.06
    POSITIVE LOGITS
    @Getter
    0.07
    ;↵↵↵↵
    0.06
    522
    0.06
     handicap
    0.06
    ++++++++
    0.06
    権
    0.06
    shine
    0.06
    	Integer
    0.06
    /v
    0.06
     },↵↵
    0.06
    Act Density 0.003%

    No Known Activations