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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kl
    -0.07
     Spir
    -0.07
     boxes
    -0.07
     Jama
    -0.06
     IEnumerable
    -0.06
    trad
    -0.06
     flashing
    -0.06
    .Scan
    -0.06
    pressive
    -0.06
     Kahn
    -0.06
    POSITIVE LOGITS
     but
    0.07
    callee
    0.06
     But
    0.06
     Yugoslavia
    0.06
     Suriye
    0.06
     mortgage
    0.06
    magnitude
    0.06
     phòng
    0.06
    Undo
    0.06
    운데
    0.06
    Act Density 0.101%

    No Known Activations