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

    Neuronpedia

    INDEX
    Explanations

    AI models and platforms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Create
    0.62
     ريا
    0.62
     Boolean
    0.60
    Create
    0.58
     esos
    0.57
     aan
    0.55
     crear
    0.54
     써
    0.54
     ماين
    0.52
     brug
    0.52
    POSITIVE LOGITS
     महापौर
    0.58
     morning
    0.56
     கரைய
    0.56
    ͕
    0.56
    Evening
    0.55
     evening
    0.53
    evening
    0.52
     morn
    0.52
    cash
    0.50
    zp
    0.50
    Act Density 0.082%

    No Known Activations