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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    remainder
    0.57
     illo
    0.55
    resulting
    0.55
    등
    0.55
     として
    0.50
     원래
    0.50
     protections
    0.50
     remainder
    0.49
    中使用
    0.48
     뭐가
    0.48
    POSITIVE LOGITS
     candidature
    0.71
     Himachal
    0.68
     aspirants
    0.68
     saree
    0.66
     Bengaluru
    0.66
     commendable
    0.66
     yester
    0.66
     said
    0.66
     sarees
    0.65
     wastage
    0.65
    Act Density 0.067%

    No Known Activations