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

    Neuronpedia

    INDEX
    Explanations

    life circumstances and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anation
    0.97
    ेड
    0.85
     lèvres
    0.84
    ্ড
    0.83
     Healing
    0.83
     गेट
    0.79
     пола
    0.79
     फाउंड
    0.79
    人人
    0.78
     DOD
    0.77
    POSITIVE LOGITS
     expectancy
    1.15
    blood
    0.96
    bu
    0.94
     ciclos
    0.86
    forms
    0.84
     revolves
    0.82
     cycle
    0.82
     revolve
    0.81
    शैली
    0.81
    cycle
    0.81
    Act Density 0.089%

    No Known Activations