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

    Neuronpedia

    INDEX
    Explanations

    photo, pharmaco, psycho

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    2.28
    ز
    2.23
    któ
    2.20
    vať
    2.08
    𝘇
    2.06
     والے
    1.96
    ς
    1.89
    ここで
    1.88
    ah
    1.86
    こちら
    1.79
    POSITIVE LOGITS
    ли
    2.02
     invertebrates
    1.94
     tigris
    1.92
     случаях
    1.89
    ])),
    1.74
     excellente
    1.74
    Dreams
    1.74
    ER
    1.72
    lots
    1.70
    Agents
    1.69
    Act Density 0.270%

    No Known Activations