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

    Neuronpedia

    INDEX
    Explanations

    ?id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Anth
    -0.08
     For
    -0.07
     Sof
    -0.07
    uar
    -0.07
    <<"
    -0.06
     toh
    -0.06
    ]"
    -0.06
    cow
    -0.06
     //
    -0.06
     incorporate
    -0.06
    POSITIVE LOGITS
     yelled
    0.07
    &M
    0.06
     videot
    0.06
    _REPO
    0.06
     jeden
    0.06
    (水
    0.06
     servants
    0.06
     sexism
    0.06
    	static
    0.06
    NEL
    0.06
    Act Density 0.002%

    No Known Activations