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

    Neuronpedia

    INDEX
    Explanations

    Google Gemma AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Grac
    0.43
     Ajax
    0.39
     bullies
    0.39
    сход
    0.37
     penerapan
    0.37
    <bbox>
    0.36
    cellSize
    0.36
    ROBERT
    0.35
    ▻
    0.35
     ROBERT
    0.35
    POSITIVE LOGITS
    Qu
    0.41
     Tos
    0.40
     TG
    0.38
     TOS
    0.37
    Warren
    0.37
    platform
    0.36
     piatta
    0.36
    gan
    0.36
    plan
    0.36
    合
    0.36
    Act Density 0.016%

    No Known Activations