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

    Neuronpedia

    INDEX
    Explanations

    volunteer / employee / disbursement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amenities
    0.48
     FROM
    0.47
    㹮
    0.46
    分开
    0.44
     realistically
    0.41
     доро
    0.41
    存储
    0.41
    开始
    0.40
    之间
    0.40
     ciphertext
    0.40
    POSITIVE LOGITS
    Employees
    0.46
    ്യത
    0.46
    Elig
    0.44
    Guj
    0.44
    Employee
    0.42
    Volunteer
    0.42
     ګرځ
    0.42
    volunteer
    0.42
     Disbursement
    0.41
    lent
    0.41
    Act Density 0.015%

    No Known Activations