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

    Neuronpedia

    INDEX
    Explanations

    unexpected

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roman
    -0.08
    in
    -0.07
    66
    -0.07
     commodities
    -0.07
     cores
    -0.06
    Clazz
    -0.06
     Carr
    -0.06
     Lori
    -0.06
    axe
    -0.06
     paved
    -0.06
    POSITIVE LOGITS
     unexpectedly
    0.09
     unexpected
    0.07
    unexpected
    0.07
    -то
    0.07
    .";
    0.07
     Unexpected
    0.07
     IKE
    0.07
     }}"><
    0.06
    emonic
    0.06
     الغ
    0.06
    Act Density 0.007%

    No Known Activations