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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обнаруж
    -0.06
     stringent
    -0.06
     persistent
    -0.06
    .notification
    -0.06
    Tiles
    -0.06
    .round
    -0.06
     Iso
    -0.06
     highways
    -0.06
    setChecked
    -0.06
    новаж
    -0.06
    POSITIVE LOGITS
    (itemView
    0.07
    Rooms
    0.07
     imageURL
    0.06
    ,:
    0.06
     순간
    0.06
    哪里
    0.06
    猪
    0.06
     자동
    0.06
     Journey
    0.06
    (win
    0.06
    Act Density 0.001%

    No Known Activations