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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses and curly braces in code

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

    Code snippets with parentheses and brackets

    np_acts-logits-general · gemini-2.0-flash

    closing brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    קישורים
    -0.57
     chiều
    -0.57
     ex
    -0.57
    IRL
    -0.57
     Ler
    -0.56
     Sp
    -0.55
     law
    -0.55
     Gel
    -0.54
    jö
    -0.54
    JOINT
    -0.53
    POSITIVE LOGITS
     feroit
    0.84
    ↵
    0.76
    };
    0.71
     auroit
    0.70
    ...}
    0.69
     الحره
    0.68
    });
    0.68
     supérieurs
    0.67
     pouvoit
    0.65
    ✨:
    0.64
    Act Density 0.101%

    No Known Activations