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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    どこ
    -0.08
     tty
    -0.07
    Maint
    -0.07
    _receive
    -0.07
     그런데
    -0.07
    ено
    -0.07
     condemn
    -0.07
     parce
    -0.07
     ELF
    -0.07
    关心
    -0.06
    POSITIVE LOGITS
    菩萨
    0.07
    等相关
    0.07
    (original
    0.06
     CAB
    0.06
    🏗
    0.06
    .resize
    0.06
    婚纱
    0.06
    针织
    0.06
    dater
    0.06
    事宜
    0.06
    Act Density 0.807%

    No Known Activations