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

    Neuronpedia

    INDEX
    Explanations

    list item prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    面的
    0.45
    Administ
    0.45
    нюю
    0.45
     दृष्टी
    0.45
     صحیح
    0.44
    Colorful
    0.43
    Appearance
    0.43
    Localization
    0.43
    Algun
    0.43
    ましい
    0.43
    POSITIVE LOGITS
     prey
    0.49
     {}".
    0.46
     octane
    0.46
    ’).
    0.43
     ticket
    0.43
     {}'.
    0.43
     peers
    0.42
    得出
    0.42
     already
    0.42
     intake
    0.42
    Act Density 0.002%

    No Known Activations