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

    Neuronpedia

    INDEX
    Explanations

    code snippets and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .:
    0.39
    :
    0.37
    .
    0.34
    arna
    0.33
    .)
    0.33
    ountains
    0.30
    Mét
    0.30
     idé
    0.30
    ؟.
    0.30
    )
    0.30
    POSITIVE LOGITS
    ל
    0.40
     після
    0.38
    ת
    0.38
     У
    0.35
    उनकी
    0.35
     এরপর
    0.34
     И
    0.34
     In
    0.34
     П
    0.34
     tattha
    0.33
    Act Density 0.083%

    No Known Activations