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

    Neuronpedia

    INDEX
    Explanations

    alignment tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    约束
    0.42
    Constraint
    0.41
    imiento
    0.41
     наві
    0.39
    谍
    0.39
     mengingat
    0.39
     Constraints
    0.39
    Constraints
    0.38
     CONSTRAINT
    0.38
    凧
    0.38
    POSITIVE LOGITS
    centerY
    0.54
     Top
    0.48
     مركز
    0.46
     height
    0.46
     Centers
    0.43
     टॉप
    0.43
     Jenny
    0.42
     Jennings
    0.42
     centers
    0.41
     centres
    0.41
    Act Density 0.003%

    No Known Activations