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

    Neuronpedia

    INDEX
    Explanations

    accessible to broad audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कांसेप्ट
    0.46
    Difference
    0.46
    Concept
    0.40
     toil
    0.40
     সমুদ
    0.39
    毫不
    0.39
     ಮಹ
    0.38
     kavram
    0.38
    θε
    0.38
    concept
    0.37
    POSITIVE LOGITS
    ců
    0.42
     Paso
    0.42
     रांची
    0.42
     घोड़
    0.40
     Nate
    0.40
     Leslie
    0.40
     Induced
    0.40
     Enfin
    0.39
    '.$
    0.39
    )}^{\
    0.39
    Act Density 0.001%

    No Known Activations