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

    Neuronpedia

    INDEX
    Explanations

    tokens that relate to programming constructs or code elements

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

    C code snippets with brackets

    np_acts-logits-general · gemini-2.0-flash

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.58
     marte
    -0.57
    хьтан
    -0.56
    modelBuilder
    -0.56
    IntoConstraints
    -0.54
     fain
    -0.53
    CppMethod
    -0.52
     pleaſure
    -0.52
     SEDS
    -0.52
    Composable
    -0.52
    POSITIVE LOGITS
     }
    0.79
     );
    0.74
     };
    0.72
     }
    0.72
     )
    0.71
     ){
    0.68
     });
    0.68
     ):
    0.66
     ];
    0.64
     );
    0.64
    Act Density 0.074%

    No Known Activations