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

    Neuronpedia

    INDEX
    Explanations

    Technical/Mathematical Language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ason
    -0.06
    subseteq
    -0.06
    -phone
    -0.06
    ulance
    -0.06
    Pawn
    -0.06
    Boxes
    -0.06
    -shaped
    -0.06
     refactor
    -0.06
    _dom
    -0.06
    .getLeft
    -0.06
    POSITIVE LOGITS
    ,...↵
    0.07
    /el
    0.07
    ])↵
    0.06
     만족
    0.06
    ाइट
    0.06
     beim
    0.06
     reset
    0.06
     vermek
    0.06
     breeze
    0.06
     ruining
    0.06
    Act Density 0.000%

    No Known Activations