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

    Neuronpedia

    INDEX
    Explanations

    [ ] brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Antibodies
    0.47
     INDIA
    0.40
     ক্যাপ্টেন
    0.38
     CONSTRUCTION
    0.38
     Slowly
    0.37
     !!!!!
    0.37
     ছাড়
    0.36
     Very
    0.36
     పొ
    0.36
     రి
    0.36
    POSITIVE LOGITS
    ge
    0.38
    不过
    0.38
    Ă
    0.38
    ov
    0.38
    engaruhi
    0.38
    范
    0.36
    enging
    0.36
    adj
    0.35
    orr
    0.35
    ailangan
    0.35
    Act Density 0.001%

    No Known Activations