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

    Neuronpedia

    INDEX
    Explanations

    App users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hal
    -0.06
     Ey
    -0.06
    =((
    -0.06
    Lin
    -0.06
    ogh
    -0.06
     manages
    -0.06
    (Scene
    -0.06
    .Align
    -0.06
    �
    -0.06
    	value
    -0.06
    POSITIVE LOGITS
    .getBytes
    0.09
     argued
    0.07
     URLSession
    0.06
    —which
    0.06
    thew
    0.06
    ابة
    0.06
    سام
    0.06
     생산
    0.06
    ][$
    0.06
    ؟
    0.06
    Act Density 0.100%

    No Known Activations