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

    Neuronpedia

    INDEX
    Explanations

    articles and possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     connect
    -0.07
    /respond
    -0.07
    _resize
    -0.07
     extending
    -0.07
     Progress
    -0.07
     summarized
    -0.07
     listened
    -0.07
     cared
    -0.06
     independ
    -0.06
     длин
    -0.06
    POSITIVE LOGITS
    .groupby
    0.07
     희
    0.07
    Stra
    0.07
    GroupBox
    0.07
    essage
    0.07
    ashire
    0.06
    ummy
    0.06
     Subaru
    0.06
     suchen
    0.06
    ぜ
    0.06
    Act Density 0.021%

    No Known Activations