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

    Neuronpedia

    INDEX
    Explanations

    code context and URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Incremental
    0.42
    團
    0.41
    ጠር
    0.39
    SCHEMA
    0.38
     preferências
    0.36
    ष्ट
    0.36
     diciembre
    0.36
    Quad
    0.36
    CCL
    0.36
    レタン
    0.35
    POSITIVE LOGITS
     hollow
    0.40
     rom
    0.38
    ယူ
    0.38
     strictest
    0.38
     aina
    0.38
     forced
    0.38
     harder
    0.38
     tougher
    0.37
    🦄
    0.37
     forward
    0.37
    Act Density 0.002%

    No Known Activations