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

    Neuronpedia

    INDEX
    Explanations

    code, formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WWW
    -0.08
    -corner
    -0.07
     susceptible
    -0.06
    -sem
    -0.06
    간
    -0.06
    -tank
    -0.06
     slaughter
    -0.06
    oids
    -0.06
    ibbean
    -0.06
    /the
    -0.06
    POSITIVE LOGITS
     yapılan
    0.06
    alsex
    0.06
    ặc
    0.06
     ціка
    0.06
     searched
    0.06
    ают
    0.06
    '],['
    0.06
     채
    0.06
    udp
    0.06
     Atlantis
    0.06
    Act Density 0.000%

    No Known Activations