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

    Neuronpedia

    INDEX
    Explanations

    beauty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swift
    -0.06
    .flat
    -0.06
     volont
    -0.06
     tslib
    -0.06
     зак
    -0.06
     succinct
    -0.06
     whisk
    -0.06
     fluct
    -0.06
    	TokenName
    -0.06
    策
    -0.06
    POSITIVE LOGITS
     beauty
    0.19
     Beauty
    0.18
    Beauty
    0.13
     Truth
    0.07
     Body
    0.07
    _geometry
    0.07
    би
    0.07
     beaut
    0.07
     exactly
    0.07
    by
    0.07
    Act Density 0.008%

    No Known Activations