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

    Neuronpedia

    INDEX
    Explanations

    intrusive thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     internet
    0.40
    Agricult
    0.38
     unveiled
    0.38
     identification
    0.37
    Squad
    0.36
     unlocked
    0.36
     situational
    0.36
     ಹೇಳ
    0.36
    ién
    0.35
     danger
    0.35
    POSITIVE LOGITS
     සැ
    0.44
    oure
    0.41
     hasonló
    0.41
     подобных
    0.41
    稍微
    0.40
     ஆயிரம்
    0.40
     हिस्से
    0.38
     비슷
    0.38
    cadherin
    0.38
    enamefont
    0.38
    Act Density 0.000%

    No Known Activations