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

    Neuronpedia

    INDEX
    Explanations

    screen Height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oc
    0.57
    cnx
    0.49
    eb
    0.47
    (
    0.45
    增
    0.44
    ൯
    0.43
      
    0.43
    (#
    0.42
    ew
    0.42
    ковка
    0.42
    POSITIVE LOGITS
    붓
    0.53
     schimb
    0.52
     ограниче
    0.51
     pravil
    0.50
     zapis
    0.49
     किला
    0.49
     judg
    0.49
     confin
    0.48
    학생
    0.48
     bă
    0.48
    Act Density 0.000%

    No Known Activations