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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dateFormat
    -0.08
     Evolution
    -0.07
     ↔
    -0.06
     vivid
    -0.06
     Arnold
    -0.06
    iph
    -0.06
     fds
    -0.06
     би
    -0.06
     antagon
    -0.06
    -prop
    -0.06
    POSITIVE LOGITS
    ποί
    0.06
    पन
    0.06
    ्मच
    0.06
    qu
    0.06
     tortured
    0.06
    جميع
    0.06
    eters
    0.06
    ँ
    0.06
    �
    0.06
    QU
    0.06
    Act Density 0.003%

    No Known Activations