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

    Neuronpedia

    INDEX
    Explanations

    Code and error messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    akens
    -0.07
    lovak
    -0.07
    818
    -0.06
     Dickens
    -0.06
    Royal
    -0.06
     epoll
    -0.06
    hest
    -0.06
    Alan
    -0.06
     cambio
    -0.06
     Střed
    -0.06
    POSITIVE LOGITS
     cash
    0.08
     specify
    0.07
     estimate
    0.07
     см
    0.07
     echt
    0.07
    449
    0.07
    ¸
    0.06
    []
    0.06
    πα
    0.06
    \core
    0.06
    Act Density 0.001%

    No Known Activations