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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    دی
    -0.06
    _mode
    -0.06
    ़त
    -0.06
     vinyl
    -0.06
     done
    -0.06
    ��
    -0.06
    lean
    -0.06
     دکتر
    -0.06
     Slut
    -0.06
    -done
    -0.06
    POSITIVE LOGITS
     marital
    0.07
    았
    0.06
    .authService
    0.06
     Этот
    0.06
    _GR
    0.06
    biên
    0.06
    precedented
    0.06
    سطس
    0.06
    .substr
    0.06
    ESH
    0.06
    Act Density 0.169%

    No Known Activations