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

    Neuronpedia

    INDEX
    Explanations

    introduce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '^
    -0.07
     tým
    -0.06
     katıl
    -0.06
     enzyme
    -0.06
    ovement
    -0.06
     peptide
    -0.06
     пенс
    -0.06
    piar
    -0.06
    uento
    -0.06
    иш
    -0.06
    POSITIVE LOGITS
    ़ो
    0.06
    Prot
    0.06
     Carl
    0.06
     Cent
    0.06
    Scientists
    0.06
    Co
    0.06
    出现
    0.06
    Implemented
    0.06
    =logging
    0.06
    rients
    0.06
    Act Density 0.016%

    No Known Activations