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

    Neuronpedia

    INDEX
    Explanations

    allowing newtrying to minimizeshrinking himself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Современ
    0.49
    ografie
    0.47
    ipedia
    0.46
     современ
    0.46
    othèque
    0.46
    诞生
    0.46
    otheby
    0.46
    enda
    0.46
    osaurus
    0.45
    akaranam
    0.45
    POSITIVE LOGITS
    െ
    0.51
     unis
    0.46
     reagents
    0.46
    تون
    0.44
    پن
    0.43
     reagent
    0.43
     devices
    0.42
    ضاف
    0.42
     assisted
    0.42
     admi
    0.42
    Act Density 0.007%

    No Known Activations