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

    Neuronpedia

    INDEX
    Explanations

    hotel room bookings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Otherwise
    -0.07
     Blur
    -0.07
     licked
    -0.06
    amente
    -0.06
     kn
    -0.06
    Tpl
    -0.06
     kari
    -0.06
    (in
    -0.06
     Sin
    -0.06
     Si
    -0.06
    POSITIVE LOGITS
     extents
    0.07
    _allowed
    0.07
    ilver
    0.06
    応
    0.06
    -archive
    0.06
    _DONE
    0.06
    olumes
    0.06
     pouze
    0.06
    dbuf
    0.06
     mostrar
    0.06
    Act Density 0.061%

    No Known Activations