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

    Neuronpedia

    INDEX
    Explanations

    code and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    サリー
    0.45
     মিলন
    0.43
    चर
    0.41
    Salary
    0.40
    сини
    0.39
     snacking
    0.39
    Storia
    0.39
     CFR
    0.39
    ักษณะ
    0.38
    šenje
    0.38
    POSITIVE LOGITS
     postponed
    0.41
     lift
    0.40
     blinked
    0.39
     too
    0.39
     very
    0.38
     dropped
    0.38
     asked
    0.38
     approached
    0.38
     addressed
    0.37
     खूप
    0.37
    Act Density 0.000%

    No Known Activations