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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Equals
    -0.07
    Mah
    -0.06
     también
    -0.06
     ks
    -0.06
    یک
    -0.06
     Lose
    -0.06
     trata
    -0.06
     fps
    -0.06
     Xm
    -0.06
    plash
    -0.06
    POSITIVE LOGITS
     hollow
    0.07
    SetActive
    0.07
     internal
    0.06
     саме
    0.06
     Lanka
    0.06
     endoth
    0.06
     입력
    0.06
     diagnosed
    0.06
    (sorted
    0.06
    /search
    0.06
    Act Density 0.143%

    No Known Activations