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

    Neuronpedia

    INDEX
    Explanations

    occurrences of code syntax related to program structure and function endings

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

    end() function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.69
    $_['
    -0.69
    -0.62
     дописавши
    -0.59
    ".
    -0.58
     
    -0.57
    =#{
    -0.56
    ⟬
    -0.56
    WEBPACK
    -0.54
    ]")]
    -0.54
    POSITIVE LOGITS
    EndContext
    0.59
    PerformLayout
    0.57
     navideño
    0.51
     península
    0.49
     húmedo
    0.48
    end
    0.46
     orilla
    0.45
     maquiagem
    0.45
     Penga
    0.45
     madrugada
    0.45
    Act Density 0.002%

    No Known Activations