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

    Neuronpedia

    INDEX
    Explanations

    generating images and text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seben
    0.85
    anc
    0.81
    ir
    0.74
    am
    0.73
    ä
    0.72
     Gauge
    0.71
     warrants
    0.69
     purified
    0.69
     Realm
    0.68
     அழைக்க
    0.68
    POSITIVE LOGITS
    ول
    0.89
    𝖔
    0.79
     tremble
    0.76
     impediment
    0.75
    ਿਆ
    0.73
    ского
    0.71
     fonctionnement
    0.71
    )$.
    0.70
    truck
    0.68
    త్తి
    0.68
    Act Density 0.001%

    No Known Activations