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

    Neuronpedia

    INDEX
    Explanations

    applies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    job
    0.41
    metric
    0.40
    STONE
    0.39
    tone
    0.39
    (`
    0.38
    NAME
    0.38
    Name
    0.37
    DOWN
    0.37
    hop
    0.37
    Wage
    0.36
    POSITIVE LOGITS
    帔
    0.44
     нео
    0.42
     பத்திர
    0.41
     пу
    0.39
     дър
    0.39
     purg
    0.38
     specially
    0.38
     cây
    0.38
    赶
    0.38
    勖
    0.38
    Act Density 0.000%

    No Known Activations