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

    Neuronpedia

    INDEX
    Explanations

    con

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     动
    -0.06
    _mesh
    -0.06
    овані
    -0.06
    ValidationError
    -0.06
     postupně
    -0.06
     moderators
    -0.06
    _WH
    -0.06
    .be
    -0.06
     XOR
    -0.06
     أجل
    -0.06
    POSITIVE LOGITS
    、ア
    0.07
    Generation
    0.06
    $,
    0.06
     construct
    0.06
    once
    0.06
    .sql
    0.06
    Philadelphia
    0.06
    sage
    0.06
     queer
    0.06
     belle
    0.06
    Act Density 0.000%

    No Known Activations