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

    Neuronpedia

    INDEX
    Explanations

    undermine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carolina
    -0.07
     cohort
    -0.07
     Skype
    -0.06
    .index
    -0.06
     日
    -0.06
     scipy
    -0.06
    	StringBuilder
    -0.06
     spaces
    -0.06
     bắt
    -0.06
     dt
    -0.06
    POSITIVE LOGITS
     통합
    0.07
     дор
    0.06
     آب
    0.06
    .Person
    0.06
    )))↵↵↵
    0.06
     Warner
    0.06
    ])↵↵↵
    0.06
    PAY
    0.06
    _GAIN
    0.06
    %)↵↵
    0.06
    Act Density 0.034%

    No Known Activations