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

    Neuronpedia

    INDEX
    Explanations

    --

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hart
    -0.07
     efficient
    -0.06
    ์พ
    -0.06
    [][]
    -0.06
     peaceful
    -0.05
     overhe
    -0.05
     проф
    -0.05
    itelist
    -0.05
    INGS
    -0.05
    _swap
    -0.05
    POSITIVE LOGITS
    대를
    0.07
     nhé
    0.07
    데이트
    0.07
     odstran
    0.07
    ในท
    0.06
     nossa
    0.06
    íst
    0.06
     nemus
    0.06
     şehir
    0.06
     ambiente
    0.06
    Act Density 0.004%

    No Known Activations