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

    Neuronpedia

    INDEX
    Explanations

    debugging code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tics
    -0.07
     wakes
    -0.07
     vehicles
    -0.07
    omics
    -0.07
    _note
    -0.07
    LOOR
    -0.07
    Match
    -0.07
     chemotherapy
    -0.06
    ницу
    -0.06
     stunt
    -0.06
    POSITIVE LOGITS
     ticari
    0.06
     созд
    0.06
     το
    0.06
    _DM
    0.06
    ραση
    0.06
     açısından
    0.06
     Serge
    0.06
    .external
    0.06
     etmesi
    0.06
    etail
    0.06
    Act Density 0.341%

    No Known Activations