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

    Neuronpedia

    INDEX
    Explanations

    God

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rape
    -0.08
    -end
    -0.07
    xford
    -0.06
     λόγ
    -0.06
    shake
    -0.06
     Economic
    -0.06
     fick
    -0.06
    (Character
    -0.06
     debian
    -0.06
     đem
    -0.06
    POSITIVE LOGITS
    ước
    0.06
    _BOUND
    0.06
     معلومات
    0.06
     ladies
    0.06
     ability
    0.06
     encrypt
    0.06
     grabbing
    0.06
     gotten
    0.06
     NOT
    0.06
    .clientY
    0.06
    Act Density 0.011%

    No Known Activations