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

    Neuronpedia

    INDEX
    Explanations

    pleasure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thiểu
    -0.07
    ونی
    -0.06
     Malcolm
    -0.06
     constitution
    -0.05
    样的
    -0.05
    -standing
    -0.05
    olik
    -0.05
     chorus
    -0.05
    legen
    -0.05
    	height
    -0.05
    POSITIVE LOGITS
     Reserve
    0.07
     skl
    0.07
    '])->
    0.07
    ूट
    0.07
    .EventArgs
    0.07
    gradation
    0.06
    คโนโลย
    0.06
    ,state
    0.06
    kses
    0.06
     STORAGE
    0.06
    Act Density 0.027%

    No Known Activations