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

    Neuronpedia

    INDEX
    Explanations

    supplementary materials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    izzes
    -0.07
    written
    -0.07
     品
    -0.07
     States
    -0.06
    .custom
    -0.06
    -Level
    -0.06
    ensors
    -0.06
     exited
    -0.06
    mrt
    -0.06
    pong
    -0.06
    POSITIVE LOGITS
    _trigger
    0.07
     permutation
    0.06
     creditor
    0.06
     Nude
    0.06
    .enter
    0.06
     tint
    0.06
     brilliantly
    0.06
     куль
    0.06
     سخ
    0.06
     saison
    0.06
    Act Density 0.006%

    No Known Activations