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

    Neuronpedia

    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writing
    -0.63
     lenker
    -0.60
    writing
    -0.55
    tagHelperRunner
    -0.55
    ArrowToggle
    -0.55
     being
    -0.52
    Writing
    -0.52
     étant
    -0.51
     Bioaccumulative
    -0.51
    being
    -0.51
    POSITIVE LOGITS
     ſever
    0.62
     greateſt
    0.57
     Hame
    0.56
     Perſ
    0.56
     ſche
    0.56
     ſtand
    0.54
     purpoſe
    0.54
     anſ
    0.54
    Hozzáférés
    0.53
    forRoot
    0.53
    Act Density 0.046%

    No Known Activations