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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Domain
    -0.08
    "G
    -0.07
    /simple
    -0.06
    .Cascade
    -0.06
    .Bar
    -0.06
    )new
    -0.06
    (RE
    -0.06
    "L
    -0.06
     respected
    -0.06
    슬
    -0.06
    POSITIVE LOGITS
    乂
    0.07
     armor
    0.07
     Shel
    0.07
    ickle
    0.06
    Collider
    0.06
    ैर
    0.06
    addafi
    0.06
     gấp
    0.06
     dissolved
    0.06
    ា
    0.06
    Act Density 0.019%

    No Known Activations