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

    Neuronpedia

    INDEX
    Explanations

    FIELD OFFICE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    f
    0.55
    ter
    0.55
    ie
    0.50
    n
    0.48
    Fil
    0.46
    wing
    0.46
    ency
    0.46
    B
    0.46
    ir
    0.45
    Ell
    0.45
    POSITIVE LOGITS
     படம்
    0.53
     সিস্টেম
    0.52
     थी
    0.49
     निकालने
    0.48
     साथ
    0.47
     insieme
    0.47
     presid
    0.46
     வைக்க
    0.46
     हाय
    0.46
     Леон
    0.46
    Act Density 0.000%

    No Known Activations