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

    Neuronpedia

    INDEX
    Explanations

    definitions and explanations of various concepts and terms

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

    Sentences ending with periods

    np_acts-logits-general · gemini-2.0-flash

    usually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HttpDelete
    -0.49
    aughan
    -0.44
    undet
    -0.43
     nonetheless
    -0.42
     anyway
    -0.42
    thered
    -0.42
     awake
    -0.41
    landet
    -0.41
    それも
    -0.41
     cages
    -0.40
    POSITIVE LOGITS
     defaultstate
    0.80
    httphttps
    0.77
    WebControls
    0.77
     Usually
    0.77
    Usually
    0.75
    ScopeManager
    0.74
    usually
    0.73
     usually
    0.72
     onOptions
    0.70
    PMailer
    0.67
    Act Density 0.617%

    No Known Activations