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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iVar
    -0.07
    Installation
    -0.06
     plague
    -0.06
    rack
    -0.06
    ीन
    -0.06
    变化
    -0.06
    ản
    -0.06
    Ố
    -0.06
    άλυ
    -0.06
     报
    -0.06
    POSITIVE LOGITS
    TOKEN
    0.07
     deutsch
    0.07
    _AUT
    0.07
     searchString
    0.06
     cedar
    0.06
     fel
    0.06
     Imports
    0.06
    .nan
    0.06
    SUMER
    0.06
     мас
    0.06
    Act Density 0.037%

    No Known Activations