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

    Neuronpedia

    INDEX
    Explanations

    happen to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     försö
    0.83
     vulnerability
    0.81
     जिससे
    0.81
    ்
    0.79
     Vulner
    0.75
    ggen
    0.75
    Pieces
    0.75
     resembling
    0.74
    ῎
    0.72
     defy
    0.72
    POSITIVE LOGITS
    ToBe
    1.32
     להיות
    1.02
     to
    1.00
    joyed
    0.92
    ることが
    0.86
    ostic
    0.84
    o
    0.83
    ToRemove
    0.82
     happens
    0.82
     goodies
    0.82
    Act Density 0.005%

    No Known Activations