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

    Neuronpedia

    INDEX
    Explanations

    symptoms-causes/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inst
    1.17
    install
    1.15
    trim
    1.15
    ust
    1.14
    your
    1.12
    flag
    1.11
    li
    1.10
    btn
    1.10
    bris
    1.09
    ↵
    1.09
    POSITIVE LOGITS
     seconda
    1.51
     segunda
    1.47
     violência
    1.45
     εξε
    1.44
     ώστε
    1.43
     αφού
    1.42
     avendo
    1.42
     pemberian
    1.42
     causando
    1.42
     procurando
    1.41
    Act Density 0.001%

    No Known Activations