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

    Neuronpedia

    INDEX
    Explanations

    something for everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    2.63
    ن
    2.58
    ار
    2.38
    tól
    2.14
    را
    2.09
    ד
    2.03
    ர்
    2.00
    ע
    1.97
    ATION
    1.96
    TE
    1.85
    POSITIVE LOGITS
    ஜ்மஹால்
    1.71
     affluent
    1.61
    otional
    1.53
     prawns
    1.53
     lysosomes
    1.53
     sphinct
    1.50
     shades
    1.48
    ஜ்மஹ
    1.48
    efficiency
    1.45
     groves
    1.45
    Act Density 0.009%

    No Known Activations