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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "If
    -0.08
    نت
    -0.07
    tsy
    -0.07
    透
    -0.07
    mitt
    -0.07
    炸
    -0.07
    .reverse
    -0.07
    쨩
    -0.07
     CT
    -0.07
     financed
    -0.07
    POSITIVE LOGITS
    �
    0.07
    (password
    0.07
    IPAddress
    0.07
    特邀
    0.07
     pageNo
    0.07
    籥
    0.07
    好象
    0.07
     BlockPos
    0.07
    _medium
    0.06
    votes
    0.06
    Act Density 0.016%

    No Known Activations