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

    Neuronpedia

    INDEX
    Explanations

    headers and footers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )$;
    0.62
    gène
    0.61
    ]$;
    0.60
     Fastest
    0.58
    KAK
    0.57
    􀂃
    0.57
     Sharks
    0.57
    gica
    0.57
    SAT
    0.55
    蔘
    0.55
    POSITIVE LOGITS
    age
    0.78
    ала
    0.77
     с
    0.69
    ak
    0.64
     primavera
    0.64
    ide
    0.62
    not
    0.62
     الم
    0.62
     bleach
    0.62
     м
    0.61
    Act Density 0.000%

    No Known Activations