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

    Neuronpedia

    INDEX
    Explanations

    draft proposal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    พิ
    0.63
     زند
    0.59
    を押
    0.56
    িকারী
    0.55
    iptic
    0.54
    ս
    0.54
     آمر
    0.53
    たたみ
    0.53
     मना
    0.53
     przech
    0.53
    POSITIVE LOGITS
     draft
    2.68
     Draft
    2.58
     drafts
    2.41
    Draft
    2.39
     proposed
    2.38
     proposal
    2.36
     proposals
    2.33
    draft
    2.31
    proposed
    2.24
     Proposed
    2.24
    Act Density 0.345%

    No Known Activations