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

    Neuronpedia

    INDEX
    Explanations

    showing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Offline
    -0.07
    contra
    -0.06
    .slice
    -0.06
     tons
    -0.06
    brates
    -0.06
    ۷
    -0.06
     дис
    -0.06
     відк
    -0.06
     lifecycle
    -0.06
     kulak
    -0.06
    POSITIVE LOGITS
    clause
    0.07
    خصوص
    0.06
    _ie
    0.06
     Yorker
    0.06
    iT
    0.06
    
    0.06
    940
    0.06
    erialized
    0.06
     появ
    0.06
     Monkey
    0.06
    Act Density 0.003%

    No Known Activations