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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ξ
    -0.07
     trio
    -0.07
    μερ
    -0.06
    έντ
    -0.06
    duğu
    -0.06
    ीआई
    -0.06
     kul
    -0.06
     interviewer
    -0.06
    -0.06
    行业
    -0.06
    POSITIVE LOGITS
     hopeless
    0.07
    евид
    0.07
    /Main
    0.07
    (coeffs
    0.06
     ApplicationRecord
    0.06
    Abs
    0.06
    _conf
    0.06
     IMPORTANT
    0.06
     Impro
    0.06
    ับม
    0.06
    Act Density 0.005%

    No Known Activations