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

    Neuronpedia

    INDEX
    Explanations

    Code snippet ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elaine
    -0.07
    γωγ
    -0.07
    _WEB
    -0.06
    _pieces
    -0.06
     JL
    -0.06
    _trip
    -0.06
     Sew
    -0.06
     tienes
    -0.06
     Ле
    -0.06
    ja
    -0.06
    POSITIVE LOGITS
     yayın
    0.07
    friendly
    0.07
    т
    0.07
    tape
    0.06
    explicit
    0.06
     testimony
    0.06
    contact
    0.06
    ounce
    0.06
    ektedir
    0.06
     signific
    0.06
    Act Density 0.063%

    No Known Activations