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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    84
    -0.06
     zwarte
    -0.06
     Suarez
    -0.06
    )!
    -0.06
    	sw
    -0.06
    Unused
    -0.06
     kvinde
    -0.06
    ]))↵↵
    -0.06
    Crear
    -0.06
    )?↵↵
    -0.06
    POSITIVE LOGITS
    sweet
    0.06
    quis
    0.06
    fo
    0.06
     criticism
    0.06
     kami
    0.06
    ế
    0.06
     prognosis
    0.06
    ху
    0.06
    胞
    0.06
     statue
    0.06
    Act Density 0.080%

    No Known Activations