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

    Neuronpedia

    INDEX
    Explanations

    LaTeX commands and formatting for figures and captions

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

    LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    LaTeX figure and equation code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     թվական
    -0.53
     account
    -0.51
    =#{
    -0.50
    {{/
    -0.49
    (.*
    -0.49
    UIFont
    -0.48
    parseDouble
    -0.46
     незавершена
    -0.46
    {}",
    -0.44
    URLEncoder
    -0.44
    POSITIVE LOGITS
     виправивши
    0.99
    ↵
    0.79
    ↵↵
    0.76
    DeleteBehavior
    0.71
    }))
    0.71
    }}}
    0.69
    },[])
    0.69
    .*")]
    0.67
     تكبرها
    0.66
    ]})
    0.65
    Act Density 0.361%

    No Known Activations