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

    Neuronpedia

    INDEX
    Explanations

    Proportions/fractions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fraction
    -0.77
    fraction
    -0.55
    ensee
    -0.54
     genes
    -0.54
     factura
    -0.53
     Lo
    -0.53
     Camp
    -0.53
    immediate
    -0.52
     ear
    -0.51
    STRUCTIONS
    -0.51
    POSITIVE LOGITS
    RegistryLite
    1.00
     Monfieur
    0.90
    IntoConstraints
    0.84
     Majefty
    0.82
     Athenians
    0.81
     purpoſe
    0.80
    theless
    0.80
     itſelf
    0.79
     ſeveral
    0.79
     uſ
    0.78
    Act Density 0.042%

    No Known Activations