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

    Neuronpedia

    INDEX
    Explanations

    delivering to recipient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ŵ
    0.40
     raids
    0.40
     moldings
    0.39
    䈤
    0.39
    があり
    0.38
    を取り
    0.38
    ചര്യ
    0.38
    ܠܐ
    0.38
     கட்டு
    0.37
     എന്ത
    0.37
    POSITIVE LOGITS
     via
    0.75
     recipient
    0.72
    via
    0.61
     recipients
    0.60
    recipient
    0.59
     VIA
    0.57
    Recipient
    0.54
     Via
    0.54
     into
    0.52
    Via
    0.50
    Act Density 0.197%

    No Known Activations