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

    Neuronpedia

    INDEX
    Explanations

    purpose-driven discrepancy planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     portable
    0.55
     miniature
    0.47
     interfacing
    0.46
     democratization
    0.45
     desktop
    0.44
     targeting
    0.44
     sotto
    0.44
    portable
    0.44
     jamming
    0.44
    яз
    0.44
    POSITIVE LOGITS
    raseña
    0.49
    ल्लाला
    0.46
    ühr
    0.46
    wdriver
    0.45
    jte
    0.45
     길이가
    0.45
    لي
    0.45
    لوم
    0.45
     ő
    0.45
    冕
    0.44
    Act Density 0.001%

    No Known Activations