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

    Neuronpedia

    INDEX
    Explanations

    postmodernism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ла
    0.84
    к
    0.82
    يد
    0.78
    з
    0.77
    ю
    0.70
    أ
    0.70
    ين
    0.69
    ES
    0.69
    є
    0.68
    키
    0.68
    POSITIVE LOGITS
     platter
    0.69
     sencillo
    0.64
    :
    0.64
    ल्पनिक
    0.59
     ditentukan
    0.58
     bathrobe
    0.57
    その
    0.57
     unus
    0.56
    です
    0.55
    ثیر
    0.55
    Act Density 0.000%

    No Known Activations