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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offset
    -0.06
     Having
    -0.06
     favorites
    -0.06
     avail
    -0.06
     Posting
    -0.06
    .Vert
    -0.06
    _calls
    -0.06
     follows
    -0.06
     intr
    -0.06
     plantation
    -0.06
    POSITIVE LOGITS
    ニュ
    0.07
     twink
    0.07
    ={({
    0.07
    794
    0.07
    ína
    0.06
     út
    0.06
    雅
    0.06
    龙
    0.06
    @js
    0.06
     Ang
    0.06
    Act Density 0.057%

    No Known Activations