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

    Neuronpedia

    INDEX
    Explanations

    It is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    emic
    -0.09
     sebou
    -0.09
    ;;;;;;;;
    -0.09
    eker
    -0.09
    702
    -0.09
    ses
    -0.09
    yy
    -0.08
    ought
    -0.08
    865
    -0.08
     dout
    -0.08
    POSITIVE LOGITS
    self
    0.20
    iner
    0.20
    inerary
    0.18
    unes
    0.17
    alic
    0.16
    åĢij
    0.15
    anium
    0.15
    /he
    0.14
    ching
    0.13
    .IsAny
    0.13
    Act Density 0.116%

    No Known Activations