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

    Neuronpedia

    INDEX
    Explanations

    requests or polite prompts

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

    please followed by an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.48
    
    -0.44
     onAnimation
    -0.42
    setVerticalGroup
    -0.40
    Карьера
    -0.39
    CppMethod
    -0.39
     diversion
    -0.39
     viewDidLoad
    -0.39
     createSlice
    -0.39
    Portale
    -0.38
    POSITIVE LOGITS
     please
    1.11
     Please
    1.10
    Please
    1.05
    please
    0.99
     bitte
    0.94
    Bitte
    0.93
     Bitte
    0.91
     PLEASE
    0.85
    PLEASE
    0.82
     Veuillez
    0.80
    Act Density 0.006%

    No Known Activations