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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    1.47
    IVING
    1.37
    >
    1.30
    er
    1.22
    OT
    1.18
    Π
    1.18
    UT
    1.13
    ัน
    1.13
    IVA
    1.13
    Ο
    1.13
    POSITIVE LOGITS
    в
    1.17
    í
    1.17
    ิ
    1.16
    новый
    1.05
    ка
    1.04
    jaty
    1.04
    мад
    1.02
    yssey
    1.02
    ן
    1.01
    ier
    0.99
    Act Density 0.082%

    No Known Activations