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

    Neuronpedia

    INDEX
    Explanations

    scientific analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Speak
    -0.07
    .account
    -0.07
    osen
    -0.06
     Anderson
    -0.06
    됨
    -0.06
    óz
    -0.06
     hành
    -0.06
    (V
    -0.06
    _PLAYER
    -0.06
     giống
    -0.06
    POSITIVE LOGITS
    킹
    0.07
    цеп
    0.06
    _Msk
    0.06
    ('/');↵
    0.06
     英语
    0.06
    kses
    0.06
    iphery
    0.05
    ыв
    0.05
     ;;^
    0.05
     IsPlainOldData
    0.05
    Act Density 0.083%

    No Known Activations