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

    Neuronpedia

    INDEX
    Explanations

    you can adjust

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modificaciones
    0.47
     modifications
    0.47
     modification
    0.45
     customization
    0.41
     adapting
    0.41
     extent
    0.41
     information
    0.40
    ancellationToken
    0.40
     contentment
    0.40
     modify
    0.40
    POSITIVE LOGITS
    Fine
    0.44
    fine
    0.40
    ٗ
    0.39
    Chron
    0.38
     Fine
    0.37
    dl
    0.36
     Narayan
    0.36
    Via
    0.36
    Extract
    0.36
     Labrenzia
    0.36
    Act Density 0.003%

    No Known Activations