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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating failures or errors in processing or operations

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

    unable to complete actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zasi
    -0.39
     Gebrauch
    -0.35
     gagner
    -0.34
     aż
    -0.32
     kế
    -0.32
     AssemblyVersion
    -0.31
     often
    -0.31
     reposer
    -0.31
     capucha
    -0.31
     Denken
    -0.31
    POSITIVE LOGITS
    expandindo
    0.80
     ब्रेकडाउन
    0.71
    TargetException
    0.64
     فريبيس
    0.62
     defaultstate
    0.57
     nahilalakip
    0.53
    AccessorTable
    0.53
    httphttps
    0.53
    揄
    0.52
    NameInMap
    0.51
    Act Density 0.010%

    No Known Activations