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

    Neuronpedia

    INDEX
    Explanations

    Planned Parenthood resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pháp
    0.66
    อล
    0.55
     produire
    0.55
     produit
    0.55
     $^{
    0.53
     đổi
    0.53
     fondateur
    0.53
     traditionnel
    0.52
     producido
    0.52
     colliding
    0.52
    POSITIVE LOGITS
    cal
    0.66
    vez
    0.59
    če
    0.59
     Bias
    0.59
     Zeiss
    0.58
    zeg
    0.57
    hearts
    0.57
     Kür
    0.57
    ka
    0.56
    vet
    0.56
    Act Density 0.005%

    No Known Activations