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

    Neuronpedia

    INDEX
    Explanations

    game rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vert
    -0.08
     Arth
    -0.07
    (Arg
    -0.07
     scrambled
    -0.07
    EDITOR
    -0.07
     Comet
    -0.07
     Otto
    -0.07
     toda
    -0.06
    cams
    -0.06
     Managers
    -0.06
    POSITIVE LOGITS
    	HX
    0.07
    compiler
    0.06
    (!_
    0.06
     souvis
    0.06
    غط
    0.06
     licens
    0.06
    .OrdinalIgnoreCase
    0.06
    وجد
    0.06
    uffers
    0.06
     운
    0.06
    Act Density 0.014%

    No Known Activations