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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    205
    -0.07
    №№
    -0.07
     passed
    -0.07
     passage
    -0.07
     Passage
    -0.07
    detach
    -0.06
     plastic
    -0.06
     수정
    -0.06
     stepper
    -0.06
    xygen
    -0.06
    POSITIVE LOGITS
    leting
    0.06
     filenames
    0.06
     fe
    0.06
    FFT
    0.06
     gf
    0.06
    arning
    0.06
    ').'</
    0.05
    PARTMENT
    0.05
     demanded
    0.05
     <*
    0.05
    Act Density 0.017%

    No Known Activations