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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    siąż
    -0.62
    tagHelperRunner
    -0.60
    stander
    -0.57
    friend
    -0.57
    +#+#
    -0.56
    standers
    -0.54
    standard
    -0.52
     poffible
    -0.52
    STANDARD
    -0.52
    rrggbb
    -0.52
    POSITIVE LOGITS
    igshid
    0.56
    脚注の使い方
    0.55
    日閲覧
    0.52
    ioutil
    0.52
    psack
    0.48
    หน
    0.47
    βο
    0.47
    ]=>
    0.46
    ximadamente
    0.46
    itates
    0.46
    Act Density 0.003%

    No Known Activations