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

    Neuronpedia

    INDEX
    Explanations

    in terms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.49
    。
    0.43
    ใน
    0.37
    >
    0.36
    8
    0.36
    $_
    0.36
    3
    0.36
    +
    0.36
            
    0.35
    .
    0.34
    POSITIVE LOGITS
     accordance
    0.45
     lieu
    0.45
     realms
    0.42
     perpetuity
    0.42
     terms
    0.41
    middels
    0.41
     свою
    0.41
     وفي
    0.40
    mediately
    0.39
    很大
    0.39
    Act Density 0.034%

    No Known Activations