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

    Neuronpedia

    INDEX
    Explanations

    equivalent purchasing power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zde
    0.40
     Calcul
    0.39
     दिलचस्पी
    0.38
     calci
    0.37
     interes
    0.37
     Visible
    0.37
     kalk
    0.36
     decid
    0.36
     hosts
    0.36
     Plattform
    0.36
    POSITIVE LOGITS
    equivalent
    0.54
    Equivalent
    0.53
     equivalent
    0.49
    compar
    0.48
    当时
    0.46
    當時
    0.43
     jeweil
    0.43
     equivalente
    0.42
    当时的
    0.41
     jeweils
    0.41
    Act Density 0.009%

    No Known Activations