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

    Neuronpedia

    INDEX
    Explanations

    riddle, puzzle, game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    They
    0.34
    Cuando
    0.34
    他们
    0.31
    ༼
    0.31
    cuando
    0.30
    Because
    0.30
     Cuando
    0.30
    blooded
    0.30
    called
    0.30
    ライダー
    0.30
    POSITIVE LOGITS
     opt
    0.32
     balconies
    0.32
     accessories
    0.32
     shower
    0.31
     bathroom
    0.30
     dryer
    0.30
     waterproofing
    0.30
     both
    0.30
     ease
    0.30
     ambience
    0.30
    Act Density 0.000%

    No Known Activations