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

    Neuronpedia

    INDEX
    Explanations

    unct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spectrum
    -0.07
     DATE
    -0.07
    	diff
    -0.07
     Hurt
    -0.06
     Classification
    -0.06
     spectra
    -0.06
     trials
    -0.06
     tariff
    -0.06
    Sys
    -0.06
     جهت
    -0.06
    POSITIVE LOGITS
     인터
    0.07
    (UnmanagedType
    0.06
    (endpoint
    0.06
    umat
    0.06
     GLint
    0.06
     탈
    0.06
    .TODO
    0.06
    援
    0.06
     tuberculosis
    0.06
     ：
    0.06
    Act Density 0.003%

    No Known Activations