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

    Neuronpedia

    INDEX
    Explanations

    code structures and syntax elements associated with programming languages

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

    code punctuation and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.53
     BoxFit
    -0.51
     nakalista
    -0.47
    hoeddwyd
    -0.46
    principalTable
    -0.46
    󠁿
    -0.45
     estrenar
    -0.44
     Raised
    -0.42
     propOrder
    -0.42
    raised
    -0.42
    POSITIVE LOGITS
     discorso
    0.42
    ]));
    0.36
     brute
    0.36
     mekan
    0.36
    ("")]
    0.33
     abstrato
    0.33
    ßerdem
    0.33
    gebob
    0.33
    UnsafeEnabled
    0.33
    ")));
    0.33
    Act Density 0.006%

    No Known Activations