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

    Neuronpedia

    INDEX
    Explanations

    code or logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -going
    -0.07
     invoking
    -0.06
     wide
    -0.06
    례
    -0.06
    掛
    -0.06
    &apos
    -0.06
    _SITE
    -0.06
     larg
    -0.06
    ुट
    -0.06
     tall
    -0.06
    POSITIVE LOGITS
    warnings
    0.07
     Grü
    0.07
    ")
↵
    0.07
    cos
    0.06
     продукты
    0.06
    ,:,:
    0.06
    ">↵↵↵
    0.06
    ）
↵
    0.06
     Aim
    0.06
     -->↵↵↵
    0.06
    Act Density 0.000%

    No Known Activations