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

    Neuronpedia

    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Byrne
    -0.07
    hest
    -0.07
    icerca
    -0.07
    財
    -0.07
    裕
    -0.07
    �
    -0.07
     Superior
    -0.06
     Elite
    -0.06
     Ко
    -0.06
    健
    -0.06
    POSITIVE LOGITS
    SPATH
    0.07
    од
    0.07
     pornofil
    0.07
     niet
    0.07
    										↵
    0.06
     override
    0.06
     deposit
    0.06
    parser
    0.06
    =>"
    0.06
    elog
    0.06
    Act Density 0.001%

    No Known Activations