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

    Neuronpedia

    INDEX
    Explanations

    medical descriptions and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.56
    at
    0.54
    On
    0.54
    ro
    0.51
    AT
    0.50
    3
    0.49
    Road
    0.49
     the
    0.47
    Op
    0.47
     capitalized
    0.47
    POSITIVE LOGITS
    中华
    0.52
    𒊹
    0.50
     ಥ
    0.50
    uları
    0.47
     Chowdh
    0.46
     💕
    0.46
    میان
    0.46
     दोन्ही
    0.45
    ußen
    0.45
     Estamos
    0.45
    Act Density 0.000%

    No Known Activations