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

    Neuronpedia

    INDEX
    Explanations

    advantageous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     die
    -0.07
    روض
    -0.07
     machine
    -0.07
     清
    -0.07
    Story
    -0.07
     Merc
    -0.06
     story
    -0.06
    foto
    -0.06
    !
    -0.06
     Liter
    -0.06
    POSITIVE LOGITS
     advantageous
    0.25
     unfavorable
    0.15
     beneficial
    0.12
     detrimental
    0.11
     conducive
    0.10
     favorable
    0.09
     favourable
    0.09
    adaptive
    0.09
    rowCount
    0.08
    _atoms
    0.07
    Act Density 0.004%

    No Known Activations