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

    Neuronpedia

    INDEX
    Explanations

    Legal disclaimers and logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Barn
    -0.06
     понима
    -0.06
     whats
    -0.06
     преж
    -0.06
     Quote
    -0.06
     tricky
    -0.06
    ところ
    -0.06
    starting
    -0.06
     cheapest
    -0.06
    ').'
    -0.06
    POSITIVE LOGITS
     CPL
    0.08
    odal
    0.07
     đèn
    0.07
    _design
    0.06
    ้อย
    0.06
    etler
    0.06
    ठ
    0.06
    '):
↵
    0.06
    ()].
    0.06
    .arrow
    0.06
    Act Density 0.000%

    No Known Activations