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

    Neuronpedia

    INDEX
    Explanations

    birds absolutely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    фак
    0.75
    ण्यासाठी
    0.70
    专用
    0.68
    orar
    0.66
     वैशिष्ट
    0.63
     পূর্বা
    0.63
    ኔ
    0.62
    ว่าจะ
    0.62
     уче
    0.61
    osters
    0.60
    POSITIVE LOGITS
    निष्
    0.66
     Raise
    0.65
     па
    0.63
     raise
    0.62
     lineage
    0.61
    连衣裙
    0.61
    ទ្ធ
    0.60
     മനു
    0.60
    airo
    0.59
     eyelid
    0.59
    Act Density 0.000%

    No Known Activations