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

    Neuronpedia

    INDEX
    Explanations

    20 Questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ερμαν
    0.54
    \%).
    0.48
    risa
    0.48
    avkhat
    0.47
    Confirm
    0.46
    UserProg
    0.46
    šenje
    0.45
    seekBar
    0.45
    userService
    0.44
     obstructing
    0.44
    POSITIVE LOGITS
    ب
    0.50
     kommen
    0.48
     by
    0.46
     el
    0.46
    by
    0.45
     zami
    0.44
     Ange
    0.43
     místo
    0.43
     az
    0.43
    වල
    0.43
    Act Density 0.001%

    No Known Activations