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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diploma
    -0.07
     hawk
    -0.06
     trò
    -0.06
     Đ
    -0.06
    cilik
    -0.06
    -Control
    -0.06
    ❤
    -0.06
     saturn
    -0.06
    aghan
    -0.06
    =-
    -0.06
    POSITIVE LOGITS
    FFT
    0.07
    (detail
    0.07
    ...↵↵↵↵
    0.07
     getProperty
    0.07
     photograph
    0.07
    äft
    0.07
     documentation
    0.07
     initializing
    0.06
    orelease
    0.06
     Release
    0.06
    Act Density 0.000%

    No Known Activations