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

    Neuronpedia

    INDEX
    Explanations

    dependency tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     altitude
    0.80
     Orient
    0.75
     Excited
    0.75
    Altitude
    0.74
     Stair
    0.74
    其他人
    0.73
     alltid
    0.73
     Exit
    0.73
     excitations
    0.73
    ارة
    0.72
    POSITIVE LOGITS
    toContain
    0.82
     बाव
    0.80
    แน่นอน
    0.79
     বিদ্যাল
    0.77
     Бушлай
    0.76
    肾
    0.76
    평
    0.73
     범
    0.73
    γά
    0.73
    龈
    0.73
    Act Density 0.000%

    No Known Activations