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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igm
    -0.07
     dispens
    -0.07
     آورد
    -0.07
    šov
    -0.06
     mpfr
    -0.06
    еф
    -0.06
    _backward
    -0.06
     safe
    -0.06
    ็บ
    -0.06
     conscience
    -0.06
    POSITIVE LOGITS
     QLD
    0.06
     UserProfile
    0.06
    第三
    0.06
    成本
    0.06
     анти
    0.06
     المج
    0.06
     Farrell
    0.06
    열
    0.06
     whisk
    0.06
    eds
    0.06
    Act Density 0.001%

    No Known Activations