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

    Neuronpedia

    INDEX
    Explanations

    want to reveal sensitive information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handball
    0.43
    edition
    0.42
    ide
    0.41
    akaranam
    0.41
     اعتبار
    0.41
    取代
    0.41
     خرا
    0.41
    uggling
    0.40
    投注
    0.40
     οπο
    0.40
    POSITIVE LOGITS
    انى
    0.45
    llium
    0.45
    כל
    0.44
    انيا
    0.43
    natur
    0.43
    ğini
    0.42
    marg
    0.42
    ruh
    0.41
    spj
    0.41
    羣
    0.41
    Act Density 0.001%

    No Known Activations