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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MALLOC
    -0.07
    ricks
    -0.06
    헌
    -0.06
     toprak
    -0.06
    -static
    -0.06
    _ud
    -0.06
    Inject
    -0.06
    ์ด
    -0.06
    nout
    -0.06
    getDb
    -0.06
    POSITIVE LOGITS
    igram
    0.06
    égor
    0.06
    /Q
    0.06
     每
    0.06
     "<?
    0.06
     objection
    0.06
     strengthens
    0.06
    distance
    0.06
    unctuation
    0.06
     predominantly
    0.06
    Act Density 0.000%

    No Known Activations