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

    Neuronpedia

    INDEX
    Explanations

    attached or detached garage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آمده
    0.60
     kaleidoscopic
    0.57
    𓏸
    0.53
    oons
    0.53
    ंसह
    0.53
     Plast
    0.52
    𝗴
    0.52
    šću
    0.52
    다라고
    0.52
     सांगतात
    0.52
    POSITIVE LOGITS
    Simplify
    0.54
    Robot
    0.50
    <0x0D>
    0.50
    ন
    0.48
    ivy
    0.48
    व
    0.48
    iv
    0.47
    न
    0.47
    Letter
    0.47
    Our
    0.46
    Act Density 0.001%

    No Known Activations