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

    Neuronpedia

    INDEX
    Explanations

    what you have in store

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    書
    0.50
     Reuse
    0.47
    ちは
    0.47
     Chir
    0.46
     Physiology
    0.46
     Platform
    0.46
    kuat
    0.46
    స్య
    0.45
    哺
    0.45
    ningar
    0.45
    POSITIVE LOGITS
    >≤</
    0.43
     pengend
    0.43
     monotonous
    0.43
    ្យ
    0.42
     chairman
    0.42
    ித்த
    0.42
     phenolic
    0.42
     chauffage
    0.41
     heating
    0.41
     便利
    0.40
    Act Density 0.001%

    No Known Activations