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

    Neuronpedia

    INDEX
    Explanations

    Code/technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GANG
    -0.06
     Was
    -0.06
    .Registry
    -0.06
     رز
    -0.06
     ورز
    -0.06
    を見る
    -0.06
    regor
    -0.06
     Ramadan
    -0.06
     �
    -0.06
     enrichment
    -0.06
    POSITIVE LOGITS
     -----
    0.07
    xffff
    0.07
     bless
    0.07
     LO
    0.07
     nell
    0.06
     августа
    0.06
     від
    0.06
    ()'
    0.06
    imers
    0.06
    .columnHeader
    0.06
    Act Density 0.000%

    No Known Activations