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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ફરિયા
    0.46
     ప్రీ
    0.41
    崤
    0.38
     atender
    0.38
     उधर
    0.37
    Bret
    0.37
     Bourd
    0.37
    ꘏
    0.37
    Hiro
    0.36
    ື່
    0.36
    POSITIVE LOGITS
    cat
    0.46
     Cat
    0.46
    Cat
    0.44
     cat
    0.42
     cats
    0.42
     catalysis
    0.41
     animal
    0.41
     defining
    0.40
     influence
    0.40
     sense
    0.40
    Act Density 0.003%

    No Known Activations