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

    Neuronpedia

    INDEX
    Explanations

    shredded or grated

    np_max-act · gemini-2.0-flash

    recipe instructions and ingredient lists for cooking.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .po
    -0.06
    apons
    -0.06
    بيرة
    -0.06
     з
    -0.06
     کامپی
    -0.06
     lofty
    -0.06
    _pos
    -0.06
     Mos
    -0.06
     cursor
    -0.06
     skupiny
    -0.06
    POSITIVE LOGITS
     shredded
    0.11
     shred
    0.08
     horrend
    0.07
     grated
    0.07
    :%
    0.07
    _gradients
    0.07
     Steelers
    0.06
    START
    0.06
    .baomidou
    0.06
    AGENT
    0.06
    Act Density 0.002%

    No Known Activations