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

    Neuronpedia

    INDEX
    Explanations

    switch statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tait
    0.39
     Cud
    0.39
    𒊑
    0.39
    តា
    0.38
    𒆤
    0.38
    iraan
    0.38
    Dimensional
    0.37
     ক্রো
    0.37
     смы
    0.37
     امیدوار
    0.37
    POSITIVE LOGITS
     case
    1.59
    case
    1.46
     caso
    1.35
     Case
    1.23
     cases
    1.22
    Case
    1.16
     경우
    1.15
     случае
    1.13
     Cases
    1.07
     případě
    1.07
    Act Density 0.013%

    No Known Activations