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

    Neuronpedia

    INDEX
    Explanations

    statistics and starting prices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     folklore
    -0.07
     benzer
    -0.06
     Hear
    -0.06
     IntelliJ
    -0.06
    One
    -0.06
     Hyp
    -0.06
    ByText
    -0.06
     films
    -0.06
     könnte
    -0.06
     Flat
    -0.06
    POSITIVE LOGITS
    нию
    0.06
    ━━
    0.06
    Games
    0.06
    ンダ
    0.06
    igraph
    0.06
    ruh
    0.06
    bj
    0.06
     among
    0.06
     strat
    0.06
    casts
    0.06
    Act Density 0.182%

    No Known Activations