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

    Neuronpedia

    INDEX
    Explanations

    math and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IPP
    -0.07
    ُه
    -0.07
    你们
    -0.06
    стин
    -0.06
    .Bean
    -0.06
    _nick
    -0.06
     inflicted
    -0.06
     branching
    -0.06
    _sign
    -0.06
    _ipc
    -0.06
    POSITIVE LOGITS
    zdy
    0.07
     웹사이트
    0.07
     courses
    0.07
    ）（
    0.07
     Points
    0.07
    ALLERY
    0.06
     Tib
    0.06
     contempor
    0.06
    лати
    0.06
     тисяч
    0.06
    Act Density 0.001%

    No Known Activations