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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nice
    -0.06
     함
    -0.06
    ↵                    ↵
    -0.06
     skys
    -0.06
    689
    -0.06
    Gui
    -0.06
     convin
    -0.06
     revolver
    -0.06
    リ
    -0.06
    lymp
    -0.06
    POSITIVE LOGITS
    _playlist
    0.08
    (constants
    0.06
    _Osc
    0.06
    .Pe
    0.06
     lắng
    0.06
     стат
    0.06
    ("<?
    0.06
     FIXED
    0.06
    ]]>
    0.06
    Rates
    0.06
    Act Density 0.026%

    No Known Activations