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

    Neuronpedia

    INDEX
    Explanations

    VS Code coding context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    না
    1.24
    ية
    1.20
    er
    1.12
    ised
    1.05
    iatric
    1.03
    ная
    1.00
    mentioned
    1.00
    з
    0.99
    lify
    0.98
    ੭
    0.96
    POSITIVE LOGITS
     lider
    1.21
     pren
    1.21
     recours
    1.18
    ट्रोल
    1.18
     liderazgo
    1.13
     peux
    1.06
     môžu
    1.05
     mamy
    1.03
    GRESS
    1.03
    ಬಹುದ
    1.03
    Act Density 0.001%

    No Known Activations