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

    Neuronpedia

    INDEX
    Explanations

    Personal Identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    um
    0.56
    ยายาม
    0.52
     contient
    0.50
     choisi
    0.50
    ichier
    0.49
    enic
    0.49
    ป้องกัน
    0.46
     assurent
    0.46
    ítulo
    0.45
     contenant
    0.45
    POSITIVE LOGITS
    愤
    0.44
    ."
    0.42
    =")"
    0.42
     cargos
    0.42
    .”
    0.41
    degenerative
    0.41
    Ahh
    0.40
     resonators
    0.39
    driver
    0.39
    ၢ
    0.39
    Act Density 0.001%

    No Known Activations