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

    Neuronpedia

    INDEX
    Explanations

    caused

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taşıy
    -0.07
    intree
    -0.06
    ektedir
    -0.06
     linker
    -0.06
     detachment
    -0.06
    lé
    -0.06
     tripod
    -0.06
     Ember
    -0.06
     repeatedly
    -0.06
     ideas
    -0.06
    POSITIVE LOGITS
     caused
    0.13
     generated
    0.07
    .Actions
    0.06
     Suit
    0.06
     Provided
    0.06
     SC
    0.06
    fried
    0.06
    "',↵
    0.06
    /AIDS
    0.06
    Caps
    0.06
    Act Density 0.009%

    No Known Activations