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

    Neuronpedia

    INDEX
    Explanations

    golang code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Customs
    0.73
     Mamm
    0.72
     Yeast
    0.72
     Investigative
    0.72
     Attitude
    0.71
     Ont
    0.71
     Sphinx
    0.70
     Kreuz
    0.70
     Cactus
    0.69
     Turn
    0.69
    POSITIVE LOGITS
    golang
    0.96
    strings
    0.95
     strconv
    0.95
    .(*
    0.95
    fmt
    0.94
     strings
    0.89
     fmt
    0.87
    strconv
    0.86
     :=
    0.84
    reflect
    0.84
    Act Density 0.035%

    No Known Activations