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

    Neuronpedia

    INDEX
    Explanations

    reasoning, purpose, modulating externally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ス
    0.52
     распо
    0.47
    Dise
    0.45
    ED
    0.45
    VC
    0.43
    VIC
    0.43
    টিয়
    0.43
     वेट
    0.43
    Fert
    0.43
     stocks
    0.42
    POSITIVE LOGITS
     nå
    0.49
     Deane
    0.47
     conm
    0.47
    лися
    0.47
     vinter
    0.46
    aking
    0.44
     ఉంట
    0.44
    jš
    0.43
     veden
    0.43
     យើង
    0.43
    Act Density 0.001%

    No Known Activations