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

    Neuronpedia

    INDEX
    Explanations

    golden cross, molecular clocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.77
    ?
    1.27
    在
    1.25
    も
    1.23
    ও
    1.12
    도
    1.06
     في
    1.03
    !
    0.98
     and
    0.96
    .
    0.92
    POSITIVE LOGITS
    er
    0.95
    𝒶
    0.94
    k
    0.88
    at
    0.88
    n
    0.86
    idän
    0.82
    y
    0.80
    aabb
    0.79
    atov
    0.79
    ból
    0.79
    Act Density 0.000%

    No Known Activations