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

    Neuronpedia

    INDEX
    Explanations

    catalytic converter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilizce
    0.64
    remeno
    0.58
     sustit
    0.55
     Portuguese
    0.54
     authoritative
    0.54
    Portuguese
    0.53
    adc
    0.51
    avic
    0.51
    같
    0.51
     Egyptian
    0.50
    POSITIVE LOGITS
     Freeway
    0.66
    ة
    0.65
     በፍ
    0.63
    𝚅
    0.60
     bored
    0.59
    ը
    0.55
    叐
    0.55
     been
    0.55
    륨
    0.55
    ድ
    0.55
    Act Density 0.002%

    No Known Activations