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

    Neuronpedia

    INDEX
    Explanations

    messages about software installation and troubleshooting issues

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

    "pas" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    ne ... pas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.56
    qrstuvwxyz
    -0.54
     W
    -0.54
    moveToFirst
    -0.52
     zost
    -0.51
     religieuses
    -0.51
     marrone
    -0.50
    ReusableCell
    -0.49
    getOut
    -0.49
     gently
    -0.47
    POSITIVE LOGITS
    homonymie
    0.65
     mapStateToProps
    0.62
    "):
    0.60
    — 
    0.60
    verwijspagina
    0.60
    ''');
    0.59
    nachron
    0.59
    -->
    0.57
    })();
    0.57
     للمعارف
    0.57
    Act Density 0.066%

    No Known Activations