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

    Neuronpedia

    INDEX
    Explanations

    explaining and describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inscription
    0.45
    ientôt
    0.43
     근무
    0.42
     inscriptions
    0.42
     overpowered
    0.40
     verhindert
    0.40
     প্রাণে
    0.40
    oplastics
    0.39
     मानने
    0.38
     determinación
    0.38
    POSITIVE LOGITS
     explain
    2.17
     discuss
    2.08
    discuss
    2.03
     discusses
    2.00
    explain
    1.98
     explains
    1.97
     describe
    1.92
     explaining
    1.87
    Discuss
    1.86
    Explain
    1.85
    Act Density 0.794%

    No Known Activations