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

    Neuronpedia

    INDEX
    Explanations

    concepts related to energy and its effects in various contexts

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

    contributions to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vit
    -0.38
    uchu
    -0.36
    ommen
    -0.35
     susun
    -0.35
    zk
    -0.34
    ingin
    -0.34
     Enable
    -0.33
     Ball
    -0.33
    mib
    -0.33
     ویکی
    -0.33
    POSITIVE LOGITS
     beginnetje
    0.62
     autorytatywna
    0.61
    InstrumentedTest
    0.55
    enterOuterAlt
    0.55
     estekak
    0.51
    RTLU
    0.50
     poffible
    0.47
    SourceChecksum
    0.47
    Bakgrunnsstoff
    0.47
    ViewFeatures
    0.47
    Act Density 0.153%

    No Known Activations