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

    Neuronpedia

    INDEX
    Explanations

    code structure and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    0.42
     so
    0.36
     thus
    0.35
     '
    0.33
     niin
    0.33
    -
    0.32
     så
    0.32
    этому
    0.31
    teil
    0.31
     that
    0.30
    POSITIVE LOGITS
     misconception
    0.38
     결과
    0.37
     vasculature
    0.37
     말투
    0.36
     meromorphic
    0.36
     драматур
    0.36
     내용
    0.35
     licenciatura
    0.35
     작업
    0.35
    醯
    0.34
    Act Density 0.048%

    No Known Activations