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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TRL
    -0.07
    }})↵
    -0.07
     STM
    -0.06
    bindung
    -0.06
    .is
    -0.06
    orghini
    -0.06
    ZF
    -0.06
     ******************************************************************************/↵↵
    -0.06
    undef
    -0.06
    pers
    -0.06
    POSITIVE LOGITS
     arsch
    0.07
     mocking
    0.07
    粉
    0.07
     özg
    0.06
    aires
    0.06
    FromString
    0.06
     Goldman
    0.06
     nok
    0.06
    олос
    0.06
     marsh
    0.06
    Act Density 0.008%

    No Known Activations