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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures within list or array-like syntax

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

    list slicing and indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stepan
    -0.44
     barri
    -0.43
    endphp
    -0.42
    GetObject
    -0.41
     Empieza
    -0.41
    곤
    -0.41
    ThemeOverlay
    -0.41
    MethodManager
    -0.40
     Rus
    -0.40
     WPA
    -0.40
    POSITIVE LOGITS
    [:
    1.06
    [:]
    0.74
     [:
    0.68
    [:-
    0.61
    [::-
    0.57
    ][:
    0.53
    genodigd
    0.52
    Beijinhos
    0.51
     Wicidata
    0.51
    ⤒
    0.49
    Act Density 0.018%

    No Known Activations