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

    Neuronpedia

    INDEX
    Explanations

    LoRA adaptation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chandelier
    0.73
     bathroom
    0.72
     Bathroom
    0.71
     मानसिक
    0.70
    ത്തിലെ
    0.69
     geotechnical
    0.69
    কুল
    0.69
    antle
    0.68
     seagulls
    0.68
     psychological
    0.68
    POSITIVE LOGITS
     ready
    0.70
    el
    0.60
    гот
    0.59
     একদিকে
    0.59
     гото
    0.58
    ogram
    0.56
     fronte
    0.55
     ಗುರು
    0.54
    otomy
    0.53
     योज
    0.52
    Act Density 0.085%

    No Known Activations