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

    Neuronpedia

    INDEX
    Explanations

    gener

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tout
    -0.07
    MD
    -0.07
    Clark
    -0.07
    _MATCH
    -0.07
    Should
    -0.07
     Zhou
    -0.07
    �
    -0.06
     spit
    -0.06
    Sheet
    -0.06
     threshold
    -0.06
    POSITIVE LOGITS
    ER
    0.09
     Gener
    0.08
    oper
    0.08
    unger
    0.07
     Mater
    0.07
    Numer
    0.07
    _duplicates
    0.07
    OPER
    0.07
    eger
    0.07
    とな
    0.07
    Act Density 0.017%

    No Known Activations