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

    Neuronpedia

    INDEX
    Explanations

    question answering pairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VRT
    -0.07
     emb
    -0.07
     qw
    -0.06
     lub
    -0.06
    arrison
    -0.06
    	put
    -0.06
     Amazing
    -0.06
     Certain
    -0.06
     Liu
    -0.06
     मर
    -0.06
    POSITIVE LOGITS
     setStatus
    0.07
    (callback
    0.06
    驚
    0.06
     UIBar
    0.06
     stale
    0.06
    ตล
    0.06
    urple
    0.06
     發
    0.06
    เคร
    0.06
    ตรง
    0.06
    Act Density 0.114%

    No Known Activations