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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ])↵↵↵
    -0.06
     Drum
    -0.06
     idiots
    -0.06
    }))↵↵
    -0.06
     pushing
    -0.06
    طم
    -0.06
     Different
    -0.06
    irtual
    -0.06
     comprehend
    -0.06
    _setting
    -0.06
    POSITIVE LOGITS
     overdue
    0.07
    (minutes
    0.07
     Swap
    0.06
    (':
    0.06
    /rules
    0.06
    ved
    0.06
    월까지
    0.06
    асти
    0.06
    脑
    0.06
     okres
    0.06
    Act Density 0.000%

    No Known Activations