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

    Neuronpedia

    INDEX
    Explanations

    terms related to coding structure or data types

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

    four bits, choices were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fédé
    -0.39
    netbeans
    -0.39
    yntaxException
    -0.39
    bukkit
    -0.38
    utives
    -0.38
     européennes
    -0.38
     primaria
    -0.38
     Sénat
    -0.37
    feeding
    -0.37
     primaire
    -0.37
    POSITIVE LOGITS
    osoba
    0.51
    Aholisi
    0.50
     choosing
    0.48
    hoeddwyd
    0.47
    uxxxx
    0.46
    CONTR
    0.46
    Choose
    0.45
    comment
    0.45
     AppComponent
    0.45
     CONTR
    0.45
    Act Density 0.006%

    No Known Activations