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

    Neuronpedia

    INDEX
    Explanations

    starts or continues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Надо
    0.81
     อยาก
    0.76
     quiso
    0.75
    䣰
    0.73
    雵
    0.72
     emphasise
    0.70
     deprive
    0.68
    toadd
    0.68
    㖅
    0.68
     undermining
    0.68
    POSITIVE LOGITS
     enters
    1.79
     enter
    1.66
     entered
    1.57
     entering
    1.56
    enters
    1.48
    Enter
    1.46
    Entering
    1.44
    enter
    1.43
    entering
    1.42
     memasuki
    1.41
    Act Density 0.128%

    No Known Activations