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

    Neuronpedia

    INDEX
    Explanations

    roja pasión

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disagrees
    0.38
    ционные
    0.37
    脨
    0.36
    escale
    0.36
    荫
    0.36
    吣
    0.35
     despair
    0.35
     shouldUse
    0.35
    苞
    0.35
     skiers
    0.35
    POSITIVE LOGITS
     possessed
    0.55
    possessed
    0.53
    even
    0.52
     even
    0.50
     burst
    0.49
     облада
    0.45
    แม้
    0.44
     даже
    0.44
     She
    0.43
     grabbed
    0.42
    Act Density 0.000%

    No Known Activations