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

    Neuronpedia

    INDEX
    Explanations

    commanding steps and interfaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉప
    0.40
     CES
    0.39
     corrective
    0.38
     chloro
    0.37
     கு
    0.37
     BACK
    0.37
     LCS
    0.37
     CLAIM
    0.36
     Wa
    0.36
     Chilli
    0.36
    POSITIVE LOGITS
    ędzynarod
    0.43
    క్క
    0.43
    ptica
    0.40
    жени
    0.39
     పూర్
    0.39
    తీ
    0.38
    движи
    0.38
    действие
    0.38
    決済
    0.37
    夺
    0.37
    Act Density 0.000%

    No Known Activations