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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eni
    -0.06
    /,↵
    -0.06
    ！↵↵
    -0.06
    $/,↵
    -0.06
     multer
    -0.06
     zví
    -0.06
    umbotron
    -0.06
    abcdefghijklmnopqrstuvwxyz
    -0.06
     finals
    -0.05
     --↵↵
    -0.05
    POSITIVE LOGITS
     additionally
    0.07
    .labelControl
    0.07
    нерг
    0.07
    .Edit
    0.06
     roughly
    0.06
     вари
    0.06
    ों,
    0.06
    RectTransform
    0.06
     Url
    0.06
    filters
    0.06
    Act Density 0.086%

    No Known Activations