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

    Neuronpedia

    INDEX
    Explanations

    Arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تحق
    -0.07
    פורס
    -0.07
     המד
    -0.07
    למו
    -0.07
    Diese
    -0.07
    ctrine
    -0.07
    (simp
    -0.07
    _VER
    -0.07
    消失了
    -0.07
     thiên
    -0.07
    POSITIVE LOGITS
    Mart
    0.07
    forma
    0.07
    ,))↵
    0.07
    strftime
    0.07
    Marsh
    0.07
    assemble
    0.07
    Regression
    0.07
    neutral
    0.07
     ADM
    0.07
     constructive
    0.07
    Act Density 0.001%

    No Known Activations