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

    Neuronpedia

    INDEX
    Explanations

    slave, freedmen, labor, training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.81
    er
    0.63
    or
    0.62
    a
    0.61
    it
    0.60
    ே
    0.59
    at
    0.59
     întreb
    0.59
     sprouted
    0.59
    l
    0.59
    POSITIVE LOGITS
     P
    0.59
     J
    0.54
     M
    0.53
    ired
    0.52
    num
    0.52
    ikh
    0.51
    すれば
    0.50
    称号
    0.49
    濃厚
    0.49
    olem
    0.49
    Act Density 0.001%

    No Known Activations