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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    td
    0.96
     dt
    0.90
     обсу
    0.82
    dT
    0.81
     subcontinent
    0.81
     সেক্রেটারি
    0.80
    ts
    0.80
     contribu
    0.80
    dt
    0.79
     cs
    0.79
    POSITIVE LOGITS
    Glucose
    0.76
    ọng
    0.75
    үү
    0.73
    ულ
    0.73
    äischen
    0.71
     সম্ভ
    0.71
    鎴
    0.71
    ूड
    0.71
    GitHub
    0.71
    GEBURTS
    0.71
    Act Density 0.000%

    No Known Activations