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

    Neuronpedia

    INDEX
    Explanations

    before: Advocate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adaptarse
    0.54
    执行
    0.45
     Tracking
    0.43
     COURT
    0.43
    烧
    0.42
    勲
    0.41
    亚
    0.41
    快
    0.41
     Adam
    0.40
     Mixed
    0.40
    POSITIVE LOGITS
    agl
    0.55
    yog
    0.54
     ogl
    0.52
    ogl
    0.52
     ಏಕೆ
    0.52
    agamanam
    0.51
    i
    0.51
    og
    0.51
    emaker
    0.50
    nici
    0.50
    Act Density 0.000%

    No Known Activations