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

    Neuronpedia

    INDEX
    Explanations

    Moves and Movement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peux
    -0.07
     Hun
    -0.07
     F
    -0.06
     Auschwitz
    -0.06
     lis
    -0.06
     frank
    -0.06
     zaw
    -0.06
    222
    -0.06
     när
    -0.06
     Lâm
    -0.06
    POSITIVE LOGITS
    Unity
    0.06
    neum
    0.06
    inant
    0.06
     vintage
    0.06
     gezocht
    0.06
    elage
    0.06
     satın
    0.06
    (process
    0.06
    ,key
    0.06
    _move
    0.06
    Act Density 0.020%

    No Known Activations