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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ying
    -0.07
    ibBundleOrNil
    -0.07
     lic
    -0.06
     Bid
    -0.06
    ig
    -0.06
     chore
    -0.06
    „A
    -0.06
     Step
    -0.06
    TabIndex
    -0.06
    	test
    -0.06
    POSITIVE LOGITS
     from
    0.25
     From
    0.20
    From
    0.17
     FROM
    0.16
    from
    0.15
    	from
    0.14
    —from
    0.13
    -from
    0.12
    FROM
    0.12
    _from
    0.11
    Act Density 0.277%

    No Known Activations