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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "fall."

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

    fall and falling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.59
    temon
    -0.54
     Tats
    -0.50
    hirts
    -0.50
     Roskov
    -0.49
    träger
    -0.49
    IUrlHelper
    -0.49
     clerks
    -0.48
     Scienti
    -0.47
     Blazer
    -0.47
    POSITIVE LOGITS
     falling
    1.35
     fall
    1.30
     Falling
    1.28
    Falling
    1.28
    Fall
    1.24
     FALL
    1.24
     Fall
    1.23
     fell
    1.20
     fallen
    1.20
    falling
    1.17
    Act Density 0.026%

    No Known Activations