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

    Neuronpedia

    INDEX
    Explanations

    listing concepts or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     което
    0.88
    （
    0.86
     selaku
    0.84
     дает
    0.82
     дают
    0.80
    你就
    0.80
     گرفتن
    0.79
    System
    0.79
    ệc
    0.78
    ifizieren
    0.76
    POSITIVE LOGITS
     symbolism
    1.13
     rhetoric
    1.01
     amenities
    1.01
     delusions
    0.98
     hardships
    0.96
     quirks
    0.96
     misery
    0.94
     visions
    0.94
     misinformation
    0.93
     craftsmanship
    0.93
    Act Density 0.101%

    No Known Activations