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

    Neuronpedia

    INDEX
    Explanations

    instances of placeholders or underscores in code

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

    is_ prefixes and boolean checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.69
     actionPerformed
    -0.60
     <<<<<<<<<<<<<<
    -0.60
    principalColumn
    -0.57
    TemporalType
    -0.57
     îna
    -0.56
    httphttps
    -0.54
     CommonModule
    -0.54
    FXML
    -0.53
     appContext
    -0.53
    POSITIVE LOGITS
     Is
    0.50
     Apakah
    0.48
    isNew
    0.47
    是小
    0.47
     está
    0.45
     suis
    0.44
     setIs
    0.44
     IS
    0.43
    Is
    0.42
    isSuccess
    0.42
    Act Density 0.006%

    No Known Activations