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

    Neuronpedia

    INDEX
    Explanations

    purpose and goals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gösteren
    -0.07
     تاب
    -0.07
    .:.:.:.:.:.:.:.:.:.:.:.:.:.:.:.:
    -0.06
    hetic
    -0.06
    AccessToken
    -0.06
    ">',↵
    -0.06
     litre
    -0.06
    91
    -0.06
    ��
    -0.06
    owan
    -0.06
    POSITIVE LOGITS
    comes
    0.07
     jTextField
    0.07
     takže
    0.06
    旧
    0.06
     concl
    0.06
    .ShouldBe
    0.06
     synd
    0.06
    __(*
    0.06
    sys
    0.06
     hlavou
    0.06
    Act Density 0.059%

    No Known Activations