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

    Neuronpedia

    INDEX
    Explanations

    references to yarn types and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    wool and sheep fibers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.55
    rrggbb
    -0.51
     aload
    -0.48
     חיצוניים
    -0.47
    ChildScrollView
    -0.45
    DockStyle
    -0.45
     plufieurs
    -0.45
     CURIAM
    -0.45
     calavera
    -0.45
     Nutt
    -0.45
    POSITIVE LOGITS
     wool
    1.45
    wool
    1.20
     Wool
    1.18
    Wool
    1.13
     sheep
    1.09
     woolen
    1.07
     Sheep
    1.02
     woollen
    0.98
    sheep
    0.93
     laine
    0.92
    Act Density 0.032%

    No Known Activations