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

    Neuronpedia

    INDEX
    Explanations

    inputs and outputs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resume
    -0.07
     liners
    -0.06
    -з
    -0.06
    stands
    -0.06
     foc
    -0.05
    چ
    -0.05
    -bars
    -0.05
     stanza
    -0.05
     comps
    -0.05
     amps
    -0.05
    POSITIVE LOGITS
    λοι
    0.07
    arus
    0.07
    Care
    0.07
    .getChild
    0.07
    .UndefOr
    0.06
     relentlessly
    0.06
     meisje
    0.06
    ==='
    0.06
     öz
    0.06
    Williams
    0.06
    Act Density 0.130%

    No Known Activations