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

    Neuronpedia

    INDEX
    Explanations

    lists of limitations or appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ملك
    0.52
    缃
    0.48
     جانے
    0.47
     मिनिस्टर
    0.46
    Owned
    0.44
    AndWait
    0.44
    ⼈
    0.44
     друз
    0.44
     Police
    0.43
    Police
    0.43
    POSITIVE LOGITS
    o
    0.49
     categorías
    0.46
     conditioning
    0.46
    k
    0.45
     crackers
    0.45
    ι
    0.45
    m
    0.44
     catastrophes
    0.44
    j
    0.44
    ?
    0.43
    Act Density 0.008%

    No Known Activations