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

    Neuronpedia

    INDEX
    Explanations

    inplace pandas operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fictitious
    0.44
    দ্ভুত
    0.44
     solicitud
    0.41
     computadora
    0.40
     cancha
    0.40
     debajo
    0.40
     sepol
    0.40
     oficiales
    0.39
     courteous
    0.39
     insuficiente
    0.39
    POSITIVE LOGITS
    G
    0.41
     পালাতে
    0.40
    வர்
    0.39
    mode
    0.39
    He
    0.38
    A
    0.38
    Dr
    0.38
    >>(
    0.38
    Neuro
    0.38
    There
    0.37
    Act Density 0.004%

    No Known Activations