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

    Neuronpedia

    INDEX
    Explanations

    closing braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podendo
    0.86
    чиго
    0.82
    </h5>
    0.81
     ஓவிய
    0.78
     रिट
    0.78
    returnData
    0.77
     mavenCentral
    0.74
    </h6>
    0.74
    ローチ
    0.73
    என்ன
    0.72
    POSITIVE LOGITS
    boxed
    0.65
     boxed
    0.62
     intake
    0.62
     diet
    0.62
     needs
    0.59
    엄
    0.59
    phere
    0.59
    }:\
    0.58
    それ
    0.57
    "+"|".
    0.57
    Act Density 0.118%

    No Known Activations