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

    Neuronpedia

    INDEX
    Explanations

    breakdown, detailed explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পূর্ব
    0.43
     Markets
    0.43
    incott
    0.43
     출발
    0.42
    йын
    0.42
     고급
    0.41
    㑨
    0.41
     blå
    0.41
    苷
    0.41
    istern
    0.41
    POSITIVE LOGITS
    Accom
    0.55
     equival
    0.49
    0
    0.49
    this
    0.49
    multiple
    0.49
     umat
    0.46
    your
    0.46
     lucru
    0.45
     dz
    0.45
     cias
    0.44
    Act Density 0.010%

    No Known Activations