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

    Neuronpedia

    INDEX
    Explanations

    Higher education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alias
    -0.31
     alias
    -0.27
     POW
    -0.27
    alia
    -0.26
    iners
    -0.25
    åģ¥
    -0.25
    ç¼ĸ
    -0.25
    _IRQHandler
    -0.24
     apologise
    -0.24
    inement
    -0.24
    POSITIVE LOGITS
    SED
    0.27
    鸥
    0.26
    rex
    0.25
     RCA
    0.25
    (bt
    0.25
     оÑĤно
    0.25
     Britann
    0.25
    fcc
    0.25
    pcm
    0.24
    ija
    0.24
    Act Density 0.023%

    No Known Activations