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

    Neuronpedia

    INDEX
    Explanations

    your Citrix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Moreover
    0.89
    .…
    0.81
     […]
    0.79
     (…)
    0.79
    )}-\
    0.78
    .’”
    0.78
    튿
    0.78
    .'”
    0.77
    ”—
    0.76
    …’
    0.74
    POSITIVE LOGITS
     we
    1.44
     I
    1.39
     only
    1.17
     not
    1.11
     its
    1.09
     they
    1.08
     attendance
    1.07
     We
    1.05
     Florida
    1.05
     Tampa
    1.05
    Act Density 0.000%

    No Known Activations