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

    Neuronpedia

    INDEX
    Explanations

    weekend plans, getaways, focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.99
     was
    0.91
    It
    0.88
     as
    0.88
    、
    0.86
    ק
    0.83
    你
    0.81
    were
    0.80
    was
    0.80
    The
    0.79
    POSITIVE LOGITS
    (
    1.24
    -
    1.24
     weekends
    1.14
    কে
    1.05
    /
    1.01
    .
    0.96
     effluents
    0.95
    ERSON
    0.92
     weekend
    0.91
     aquifers
    0.88
    Act Density 0.002%

    No Known Activations