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

    Neuronpedia

    INDEX
    Explanations

    checking for empty or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PAUL
    0.41
    Approach
    0.40
    thyl
    0.39
    Pel
    0.39
    ciples
    0.38
    爣
    0.38
    鄔
    0.38
    Rod
    0.38
    approach
    0.38
    ]-\
    0.37
    POSITIVE LOGITS
     exists
    0.79
     vorhanden
    0.72
     exist
    0.70
     suficientes
    0.66
     esiste
    0.66
     existe
    0.66
     exista
    0.66
     enough
    0.65
     existir
    0.64
    exists
    0.64
    Act Density 0.038%

    No Known Activations