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

    Neuronpedia

    INDEX
    Explanations

    wiki

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lad
    -0.08
    んじゃない
    -0.08
    凛
    -0.07
     alleging
    -0.07
    _FMT
    -0.07
     взять
    -0.06
    /cat
    -0.06
    יץ
    -0.06
     freezing
    -0.06
    בלים
    -0.06
    POSITIVE LOGITS
    	Color
    0.07
     magnesium
    0.07
    gi
    0.07
    ﻯ
    0.07
     scrollbar
    0.07
     Rivera
    0.06
    orthy
    0.06
    iya
    0.06
    .Line
    0.06
    ge
    0.06
    Act Density 0.001%

    No Known Activations