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

    Neuronpedia

    INDEX
    Explanations

    place names and geographical locations

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

    KL, NZ, Helsinki, Edmond, Tex, Pa, Fla, Finnish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     good
    -0.35
    見
    -0.35
     ep
    -0.35
    ↵↵
    -0.34
     very
    -0.34
    好
    -0.33
    <eos>
    -0.33
    回
    -0.32
    <em>
    -0.32
    行
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.77
     erſt
    0.77
    niſſe
    0.74
     nahilalakip
    0.73
    IsContent
    0.72
     desmotivaciones
    0.70
     dieſer
    0.68
     Normdatei
    0.68
     increí
    0.68
     ſeine
    0.68
    Act Density 0.804%

    No Known Activations