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

    Neuronpedia

    INDEX
    Explanations

    N

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stricter
    -0.06
    _DET
    -0.06
     перен
    -0.06
     convinced
    -0.06
    菌
    -0.06
    ्रमण
    -0.06
    _pg
    -0.06
     convince
    -0.06
     TOR
    -0.06
     Interestingly
    -0.06
    POSITIVE LOGITS
     ilç
    0.07
    _FIX
    0.07
    ]</
    0.07
     coils
    0.06
    	labels
    0.06
    abolic
    0.06
     WITHOUT
    0.06
    =end
    0.06
     Rotate
    0.06
    ocate
    0.06
    Act Density 0.000%

    No Known Activations