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

    Neuronpedia

    INDEX
    Explanations

    transfer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    className
    -0.08
     euro
    -0.07
    _cb
    -0.07
    .kr
    -0.07
     %↵↵
    -0.07
    ì
    -0.07
    -extra
    -0.07
    枚
    -0.06
     '}';↵
    -0.06
    โซ
    -0.06
    POSITIVE LOGITS
    北美
    0.07
     pornofil
    0.07
    arbeit
    0.07
     hare
    0.07
     SCORE
    0.07
     loading
    0.06
     prostitutes
    0.06
    填报
    0.06
     nood
    0.06
     teaches
    0.06
    Act Density 0.017%

    No Known Activations