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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scrolling
    -0.08
     gibi
    -0.08
    CTYPE
    -0.08
     kartaa
    -0.08
    inon
    -0.07
     każdy
    -0.07
    like
    -0.07
     cias
    -0.07
    皆
    -0.07
     antid
    -0.07
    POSITIVE LOGITS
    Remaining
    0.11
     remaining
    0.10
    剩
    0.10
     leftover
    0.10
     осталось
    0.10
     restantes
    0.09
    remaining
    0.09
     leftovers
    0.09
    _remaining
    0.09
     restant
    0.09
    Act Density 0.046%

    No Known Activations