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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Qaeda
    -0.06
     Roman
    -0.06
    idders
    -0.06
     Bread
    -0.06
    zp
    -0.06
     Nikola
    -0.06
    in
    -0.06
     mieux
    -0.06
     Iraqi
    -0.06
     Photon
    -0.06
    POSITIVE LOGITS
    oeff
    0.07
     Ж
    0.07
     neob
    0.07
    _REC
    0.06
     Muham
    0.06
    οκ
    0.06
    .Blue
    0.06
     memberships
    0.06
    /svg
    0.06
     [<
    0.06
    Act Density 0.001%

    No Known Activations