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

    Neuronpedia

    INDEX
    Explanations

    linked directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rite
    0.40
     Patria
    0.40
     cama
    0.40
    yte
    0.40
     شبه
    0.40
     Apt
    0.38
    >);
    0.38
    єте
    0.38
    isses
    0.38
     उपयुक्त
    0.38
    POSITIVE LOGITS
    !“
    0.45
    SQL
    0.44
    _'
    0.40
    !"
    0.38
    django
    0.38
    UNO
    0.38
    金属
    0.38
    WATER
    0.38
    !".
    0.37
    .“
    0.37
    Act Density 0.002%

    No Known Activations