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

    Neuronpedia

    INDEX
    Explanations

    opening tag delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worsening
    1.06
     centrifugation
    1.02
    其余
    1.00
     allt
    0.94
     나머지
    0.92
     flashbacks
    0.91
    同
    0.91
    其他的
    0.90
    ங்கிணை
    0.89
     поиск
    0.89
    POSITIVE LOGITS
    с
    1.03
    🔥🔥
    0.93
    по
    0.81
    slash
    0.81
    os
    0.81
    वत्ता
    0.76
    器的
    0.75
    obaan
    0.74
    ार
    0.74
    weed
    0.74
    Act Density 0.015%

    No Known Activations