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

    Neuronpedia

    INDEX
    Explanations

    apple slices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asgi
    1.01
    ,—
    1.00
    —
    0.99
     —
    0.93
    ;
    0.91
     оюн
    0.89
    ,
    0.88
     შეი
    0.85
    .—
    0.85
     ACID
    0.81
    POSITIVE LOGITS
    ल्लू
    1.45
     chiếc
    1.42
     الدكتور
    1.35
     एन
    1.33
     শ্রীযুক্ত
    1.31
     শ্রীমতি
    1.31
    Patricia
    1.28
     penghargaan
    1.28
     ಕರಿ
    1.27
     Patricia
    1.26
    Act Density 0.186%

    No Known Activations