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

    Neuronpedia

    INDEX
    Explanations

    reptiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    1.20
    ו
    1.17
     Хабаровского
    1.14
     applicator
    1.13
    所
    1.12
    소
    1.12
     strawberries
    1.11
    Giải
    1.09
    品
    1.09
     darkest
    1.09
    POSITIVE LOGITS
    is
    1.88
    on
    1.45
    l
    1.44
    ens
    1.40
    k
    1.34
    has
    1.32
    was
    1.31
    os
    1.29
    ce
    1.29
    rept
    1.26
    Act Density 0.002%

    No Known Activations