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

    Neuronpedia

    INDEX
    Explanations

    instances of actions or states involving visibility and perception

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

    perception or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contests
    -0.39
    MemoryWarning
    -0.39
     contemporaine
    -0.39
     citoy
    -0.38
     contest
    -0.38
     uffic
    -0.37
     Oficial
    -0.37
    的问道
    -0.37
     surla
    -0.36
     rechazo
    -0.36
    POSITIVE LOGITS
     clip
    0.49
     clips
    0.48
     يتيمه
    0.48
     виправивши
    0.47
     indistinct
    0.47
     OMITBAD
    0.47
     narrator
    0.44
    AccessorTable
    0.44
    SharedCtor
    0.43
    GroupLayout
    0.43
    Act Density 0.199%

    No Known Activations