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

    Neuronpedia

    INDEX
    Explanations

    original or principal amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    はこの
    0.44
    binghamton
    0.39
    လည်း
    0.38
     neigh
    0.38
     تكون
    0.36
    zingen
    0.36
     निश्चित
    0.36
     αυτή
    0.35
     زیادی
    0.35
     صحبت
    0.35
    POSITIVE LOGITS
     метою
    0.39
    ។
    0.38
    об
    0.38
    вар
    0.38
    Formation
    0.37
    ⎆
    0.37
    ADES
    0.37
    ев
    0.37
    Fraud
    0.37
    Eligibility
    0.36
    Act Density 0.001%

    No Known Activations