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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Citizens
    -0.07
     kom
    -0.06
     utterly
    -0.06
     numRows
    -0.06
    Unlock
    -0.06
     Landscape
    -0.06
     sounded
    -0.06
     VERIFY
    -0.06
    char
    -0.06
     Catherine
    -0.06
    POSITIVE LOGITS
     якій
    0.07
    .at
    0.06
    160
    0.06
    rich
    0.06
    .Ref
    0.06
     Cooking
    0.06
     flex
    0.06
    hod
    0.06
    ním
    0.06
    -year
    0.06
    Act Density 0.000%

    No Known Activations