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

    Neuronpedia

    INDEX
    Explanations

    things that change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becomes
    1.41
     become
    1.38
     becoming
    1.30
     became
    1.27
     Becoming
    1.26
    becomes
    1.25
    Becoming
    1.25
    become
    1.25
    Become
    1.16
     devenu
    1.16
    POSITIVE LOGITS
     целе
    0.73
     utilising
    0.71
     kajian
    0.71
     وبي
    0.69
    뿐
    0.69
     prototypical
    0.68
    ilian
    0.68
     tự
    0.67
     utilizing
    0.66
    經常
    0.66
    Act Density 0.086%

    No Known Activations