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

    Neuronpedia

    INDEX
    Explanations

    documentation excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     committed
    -0.07
     stomach
    -0.07
    ovice
    -0.07
     rid
    -0.07
    emaakt
    -0.06
    룸
    -0.06
    ική
    -0.06
     resume
    -0.06
    moire
    -0.06
    찰
    -0.06
    POSITIVE LOGITS
    _SL
    0.07
     покры
    0.06
    Vec
    0.06
     sapi
    0.06
     будущ
    0.06
    -envelope
    0.06
     defy
    0.06
    <(),
    0.06
    _WITH
    0.05
     підприєм
    0.05
    Act Density 0.053%

    No Known Activations