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

    Neuronpedia

    INDEX
    Explanations

    sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     headache
    -0.06
     expertise
    -0.06
     Rewards
    -0.06
     pressures
    -0.06
    antanamo
    -0.06
     طرف
    -0.06
    nosis
    -0.06
     통해
    -0.06
     wraps
    -0.06
    >Date
    -0.05
    POSITIVE LOGITS
     presidential
    0.07
    SingleOrDefault
    0.07
    rez
    0.07
     Addiction
    0.07
     dovol
    0.07
     American
    0.06
     Sez
    0.06
    \Plugin
    0.06
     iota
    0.06
    (Dictionary
    0.06
    Act Density 0.000%

    No Known Activations