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

    Neuronpedia

    INDEX
    Explanations

    Protests/demonstrations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mim
    -0.06
     싸
    -0.06
    чя
    -0.06
    ifting
    -0.06
    �
    -0.06
    amburger
    -0.06
     δε
    -0.06
     undead
    -0.06
    Outside
    -0.06
    thest
    -0.06
    POSITIVE LOGITS
    zano
    0.08
     ginger
    0.06
     требуется
    0.06
     philosopher
    0.06
     projections
    0.06
     устройства
    0.06
     callbacks
    0.06
    ponder
    0.06
    atories
    0.06
    086
    0.06
    Act Density 0.014%

    No Known Activations