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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing problems, challenges, or negative outcomes

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

    issues encountered or happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.43
     autorytatywna
    -0.42
     ffilm
    -0.38
    MENAFN
    -0.37
    Bibliograf
    -0.36
     estekak
    -0.36
     Normdatei
    -0.35
     Osama
    -0.35
     verfü
    -0.34
    Autoritní
    -0.34
    POSITIVE LOGITS
     createSlice
    0.52
    instancetype
    0.48
    ksikon
    0.47
     disambiguazione
    0.47
     nakalista
    0.45
    0.44
    Clik
    0.43
     davantage
    0.43
     blessure
    0.43
    irmanship
    0.42
    Act Density 0.128%

    No Known Activations