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

    Neuronpedia

    INDEX
    Explanations

    math questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (
    -0.07
     biscuits
    -0.07
    olum
    -0.07
     caches
    -0.06
     vaccine
    -0.06
     columns
    -0.06
     рівень
    -0.06
     LE
    -0.06
     served
    -0.06
     timp
    -0.06
    POSITIVE LOGITS
    Unmount
    0.07
     insecurity
    0.06
    :NSLayout
    0.06
    웨
    0.06
    	INT
    0.06
    ruptcy
    0.06
    :X
    0.06
    chmod
    0.06
    ствен
    0.06
    _TICK
    0.06
    Act Density 0.135%

    No Known Activations