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

    Neuronpedia

    INDEX
    Explanations

    phrasing after lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etcétera
    1.26
     OSS
    1.25
     Astronaut
    1.20
     ESL
    1.18
    C
    1.18
     Cess
    1.17
     Cassandra
    1.16
    ﺓ
    1.16
     Certains
    1.15
     Oasis
    1.13
    POSITIVE LOGITS
    ل
    1.08
    ко
    1.00
    datos
    0.98
    ัน
    0.97
    ження
    0.96
    ि
    0.95
    conten
    0.94
    ien
    0.93
    ek
    0.93
    বহুল
    0.93
    Act Density 0.514%

    No Known Activations