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

    Neuronpedia

    INDEX
    Explanations

    Fields of study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cute
    -0.07
     �
    -0.06
     Helvetica
    -0.06
    cleanup
    -0.06
    orary
    -0.06
    扱
    -0.06
    .Logic
    -0.06
    _builder
    -0.06
    一级
    -0.06
     spreading
    -0.06
    POSITIVE LOGITS
    Comment
    0.07
    Ком
    0.07
    Smoke
    0.07
    isateur
    0.07
    最
    0.07
    Positions
    0.07
    autocomplete
    0.06
     Weak
    0.06
    Pour
    0.06
    <table
    0.06
    Act Density 0.015%

    No Known Activations