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

    Neuronpedia

    INDEX
    Explanations

    Code/rules/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADF
    -0.07
    (ValueError
    -0.06
    'on
    -0.06
    202
    -0.06
    ὲ
    -0.06
     lz
    -0.06
     notable
    -0.06
    .questions
    -0.06
    herent
    -0.06
    уса
    -0.06
    POSITIVE LOGITS
     Gore
    0.07
     Wenn
    0.07
    _ALIGN
    0.07
     troll
    0.06
    .shader
    0.06
     ALWAYS
    0.06
    .DropDown
    0.06
    *****
    0.06
    acom
    0.06
    Wenn
    0.06
    Act Density 0.000%

    No Known Activations