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

    Neuronpedia

    INDEX
    Explanations

    probability/math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Model
    -0.07
     authors
    -0.07
     model
    -0.07
    .sys
    -0.06
    (rect
    -0.06
     Rodrigo
    -0.06
     Braz
    -0.06
     Believe
    -0.06
     Alexand
    -0.06
     authored
    -0.06
    POSITIVE LOGITS
    衝
    0.07
    раз
    0.06
    ा↵
    0.06
     vlast
    0.06
     Morm
    0.06
    -da
    0.06
     hearty
    0.06
    .contentSize
    0.06
    урс
    0.06
    thest
    0.06
    Act Density 0.010%

    No Known Activations