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

    Neuronpedia

    INDEX
    Explanations

    programming/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cou
    -0.07
    snap
    -0.07
     form
    -0.07
    lady
    -0.06
    Blend
    -0.06
     рекоменду
    -0.06
     base
    -0.06
    _long
    -0.06
    truncate
    -0.06
     Memories
    -0.06
    POSITIVE LOGITS
     unsuccessfully
    0.07
     assignable
    0.07
    ęd
    0.06
     onstage
    0.06
     sữa
    0.06
     제가
    0.06
     MG
    0.06
    élé
    0.06
     vždy
    0.06
     minib
    0.06
    Act Density 0.091%

    No Known Activations