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

    Neuronpedia

    INDEX
    Explanations

    cooking and spicy foods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鐮
    0.33
    獼
    0.31
    螓
    0.31
    鈽
    0.30
    윕
    0.30
    撣
    0.29
    磔
    0.29
    錨
    0.29
    鉭
    0.29
    াকিং
    0.29
    POSITIVE LOGITS
     and
    0.29
    _
    0.29
    ，
    0.26
     indulge
    0.26
     exh
    0.24
     और
    0.24
    ↵↵
    0.23
    &
    0.23
     stuffs
    0.23
     indulged
    0.23
    Act Density 0.040%

    No Known Activations