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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loot
    0.57
     brush
    0.55
     lighten
    0.54
    azos
    0.53
    മ്പര
    0.53
     ac
    0.53
    tpl
    0.53
     gram
    0.52
    茥
    0.52
    बताया
    0.52
    POSITIVE LOGITS
     Pulmonary
    0.68
     Murdock
    0.67
     או
    0.66
     낙
    0.63
     ஏ
    0.63
     உரு
    0.61
     선생님
    0.59
    attha
    0.59
     CONSEQUENTIAL
    0.59
    рып
    0.59
    Act Density 0.000%

    No Known Activations