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

    Neuronpedia

    INDEX
    Explanations

    closing brackets used in code formatting

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

    user input after start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apore
    -0.49
     Rockville
    -0.47
     SPM
    -0.47
     Spokane
    -0.46
     mansions
    -0.46
    lees
    -0.46
    wand
    -0.46
    COUVER
    -0.46
     OpenGL
    -0.46
     Hollywood
    -0.45
    POSITIVE LOGITS
    ]{
    0.54
    behavior
    0.49
     behavior
    0.48
     Behavior
    0.44
    +:+
    0.42
     BEHAVIOR
    0.41
     față
    0.39
    Hozzáférés
    0.39
    脚注の使い方
    0.39
     creș
    0.38
    Act Density 0.000%

    No Known Activations