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

    Neuronpedia

    INDEX
    Explanations

    conven

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     định
    -0.07
     originals
    -0.06
    _fixed
    -0.06
    跡
    -0.06
    erts
    -0.06
    olygon
    -0.06
    indicator
    -0.06
    ึง
    -0.05
    .parseInt
    -0.05
    stre
    -0.05
    POSITIVE LOGITS
     Garten
    0.07
    (latitude
    0.07
    kowski
    0.07
    rocessing
    0.07
    Interfaces
    0.07
    exual
    0.07
    _adapter
    0.07
    Challenge
    0.06
     Hook
    0.06
     harvesting
    0.06
    Act Density 0.001%

    No Known Activations