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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Includes
    -0.07
    Ek
    -0.06
     připoj
    -0.06
    �
    -0.06
     graveyard
    -0.06
    inity
    -0.06
    _alarm
    -0.06
     процед
    -0.06
     �
    -0.06
     دقی
    -0.06
    POSITIVE LOGITS
    .pic
    0.07
    LL
    0.06
    MBED
    0.06
     bh
    0.06
     thí
    0.06
    startdate
    0.06
    !"
    0.06
     single
    0.06
    _REPLY
    0.06
    @@
    0.06
    Act Density 0.050%

    No Known Activations