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

    Neuronpedia

    INDEX
    Explanations

    like pointy ears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    1.41
    ™.
    1.40
    &
    1.27
    (!
    1.23
    .
    1.23
    (&
    1.23
    (
    1.22
     &/
    1.22
    .;
    1.21
    .)
    1.19
    POSITIVE LOGITS
    AllCaps
    1.11
    ᠬ
    1.10
    بیر
    1.09
    ריך
    1.08
     crouching
    1.05
     расстоянии
    1.04
    менить
    1.02
    мене
    1.01
    наче
    1.00
     Мол
    1.00
    Act Density 0.187%

    No Known Activations