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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ومن
    -0.07
    .construct
    -0.06
    _AF
    -0.06
    _EN
    -0.06
     censor
    -0.06
     Ев
    -0.06
    ?.
    -0.06
     Euler
    -0.06
    _owned
    -0.06
     sophisticated
    -0.06
    POSITIVE LOGITS
     deco
    0.06
     richTextBox
    0.06
     техничес
    0.06
     Biblical
    0.06
    운
    0.06
     bodily
    0.06
    (GameObject
    0.06
    (g
    0.06
    洞
    0.05
     personel
    0.05
    Act Density 0.033%

    No Known Activations