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

    Neuronpedia

    INDEX
    Explanations

    Questions about time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     textbooks
    -0.07
    upos
    -0.07
    っ�
    -0.07
     But
    -0.06
     ult
    -0.06
     rejected
    -0.06
     Больш
    -0.06
    luck
    -0.06
    ↵↵↵↵↵↵↵↵↵↵
    -0.06
    anz
    -0.06
    POSITIVE LOGITS
    ця
    0.07
     musician
    0.06
    .pm
    0.06
    .sync
    0.06
    creen
    0.06
    .slice
    0.06
     труда
    0.06
     sym
    0.06
    Tile
    0.06
     Buccaneers
    0.06
    Act Density 0.029%

    No Known Activations