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

    Neuronpedia

    INDEX
    Explanations

    compounding interest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     escena
    0.47
     composers
    0.44
     gore
    0.43
     composites
    0.43
     scene
    0.42
     composite
    0.40
     Brow
    0.40
     сро
    0.39
     Ira
    0.39
     ép
    0.38
    POSITIVE LOGITS
    rictions
    0.41
    危
    0.38
    rically
    0.38
     வித
    0.38
    अंत
    0.38
    拚
    0.38
    cter
    0.38
     کولو
    0.38
    ffen
    0.38
    캅
    0.38
    Act Density 0.000%

    No Known Activations