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

    Neuronpedia

    INDEX
    Explanations

    select

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     અરજી
    -0.08
     reimbursement
    -0.08
     folds
    -0.08
     plaintiffs
    -0.08
     woll
    -0.08
     pays
    -0.07
     obtenir
    -0.07
    申请
    -0.07
     explo
    -0.07
     شهادة
    -0.07
    POSITIVE LOGITS
    任
    0.15
    用
    0.14
    选
    0.12
    产生
    0.11
     bổ
    0.11
     任
    0.10
    appointment
    0.10
     appointment
    0.10
    appointments
    0.10
    選
    0.10
    Act Density 0.006%

    No Known Activations