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

    Neuronpedia

    INDEX
    Explanations

    inhibition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یز
    -0.07
     ALIGN
    -0.06
     ActivatedRoute
    -0.06
     Flour
    -0.06
    .only
    -0.06
     Nov
    -0.06
    crollView
    -0.06
    	nodes
    -0.06
    unds
    -0.06
    Mocks
    -0.06
    POSITIVE LOGITS
     těla
    0.07
    技术
    0.06
    .must
    0.06
    องท
    0.06
     협
    0.06
     waterfront
    0.06
    ventario
    0.06
    جة
    0.06
     hoş
    0.06
     rethink
    0.06
    Act Density 0.015%

    No Known Activations