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

    Neuronpedia

    INDEX
    Explanations

    various punctuation marks and symbols

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

    Programming code and related terms

    np_acts-logits-general · gemini-2.0-flash

    programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.91
    fromnode
    -0.91
     مرئيه
    -0.86
     digress
    -0.80
     parseFrom
    -0.80
    Hentet
    -0.78
    ())),
    -0.74
    ])),
    -0.72
    Sucesor
    -0.71
     ""))
    -0.70
    POSITIVE LOGITS
    GEBURTS
    0.78
     setPassword
    0.51
    dopodob
    0.50
     CascadeType
    0.50
    География
    0.48
    estris
    0.47
    ومه
    0.47
    UIN
    0.47
    olester
    0.46
    GEBURTSDATUM
    0.46
    Act Density 0.155%

    No Known Activations