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

    Neuronpedia

    INDEX
    Explanations

    commands and functions related to logging outputs in programming

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

    printing statements followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
    SourceChecksum
    -0.61
    EnableWeb
    -0.55
     propOrder
    -0.54
     Roskov
    -0.49
     resourceCulture
    -0.47
    stateProvider
    -0.45
     ProtoMessage
    -0.45
     Italijani
    -0.45
    UnusedPrivate
    -0.45
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.50
    insegna
    0.49
    altezza
    0.46
    ufficio
    0.44
     gebru
    0.44
     jaula
    0.44
    agus
    0.43
                         
    0.43
     Institution
    0.43
    zij
    0.43
    Act Density 0.006%

    No Known Activations