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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ､↵
    -0.07
     equity
    -0.07
                                ↵
    -0.07
    ]↵↵↵
    -0.06
     yavaş
    -0.06
    ).</
    -0.06
    िल
    -0.06
    地下
    -0.06
    ypy
    -0.06
     coarse
    -0.06
    POSITIVE LOGITS
     sow
    0.07
     sodom
    0.06
    +self
    0.06
     Sü
    0.06
    essenger
    0.06
     Brisbane
    0.06
    .Dictionary
    0.06
     Hava
    0.06
     discreet
    0.06
     uttered
    0.06
    Act Density 0.178%

    No Known Activations