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

    Neuronpedia

    INDEX
    Explanations

    .)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ana
    -0.07
    oun
    -0.06
    ansion
    -0.06
    Slot
    -0.06
    argo
    -0.06
     función
    -0.06
    gne
    -0.06
     Squad
    -0.06
    (show
    -0.06
     reven
    -0.06
    POSITIVE LOGITS
     assertNotNull
    0.06
     retros
    0.06
     mortgage
    0.06
    ійської
    0.06
        ↵↵
    0.06
     ),↵
    0.06
     california
    0.06
     �
    0.06
    ˆ
    0.06
    .ecore
    0.06
    Act Density 0.001%

    No Known Activations