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

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anst
    -0.07
     histograms
    -0.07
     anch
    -0.06
     coc
    -0.06
     tane
    -0.06
     Sloan
    -0.06
     pound
    -0.06
    _threads
    -0.06
    мо
    -0.06
     walking
    -0.06
    POSITIVE LOGITS
     Overwatch
    0.07
     actionable
    0.07
     tactile
    0.07
     něm
    0.07
     onemocnění
    0.07
    .Lines
    0.07
     nově
    0.07
     village
    0.07
     Kuzey
    0.07
     玩家
    0.07
    Act Density 0.009%

    No Known Activations