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

    Neuronpedia

    INDEX
    Explanations

    frequently appearing keys or placeholders within a structured text format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    advantage that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataPropertyName
    -0.40
     Tiefe
    -0.38
    ždý
    -0.36
     participation
    -0.34
    fastjson
    -0.33
     dedans
    -0.33
     Schicksal
    -0.33
     biens
    -0.33
     leading
    -0.33
    nmgp
    -0.33
    POSITIVE LOGITS
    tvguidetime
    0.76
     Италијани
    0.76
     lenker
    0.68
    ViewFeatures
    0.67
    uxxxx
    0.59
    الدراسه
    0.59
     protoimpl
    0.59
    awtextra
    0.57
     <<<<<<<<<<<<<<
    0.56
    fjspx
    0.56
    Act Density 0.000%

    No Known Activations