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

    Neuronpedia

    INDEX
    Explanations

    html head closing tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    📥
    0.38
     Melrose
    0.36
    ꩡ
    0.36
     pituitary
    0.36
    餾
    0.36
    0.35
    ੲ
    0.35
     ވަ
    0.35
     資
    0.35
    ലീസ്
    0.34
    POSITIVE LOGITS
    ↵↵
    0.42
    k
    0.38
    ég
    0.37
    config
    0.36
    id
    0.36
    ↵↵↵
    0.35
    ↵
    0.35
    im
    0.35
    io
    0.34
    ise
    0.34
    Act Density 0.004%

    No Known Activations