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

    Neuronpedia

    INDEX
    Explanations

    german language and German addresses or institutions

    oai_token-act-pair · gemini-2.0-flash

    German

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prozess
    -0.95
    anhänger
    -0.93
    pumpe
    -0.90
    mädchen
    -0.90
    gerät
    -0.83
    streifen
    -0.82
    bedarf
    -0.81
    behälter
    -0.80
     дописавши
    -0.80
    preise
    -0.80
    POSITIVE LOGITS
    <bos>
    0.82
    Koordinaten
    0.58
     scuro
    0.52
    hold
    0.51
    ahalli
    0.49
    RegistryLite
    0.48
    хозяй
    0.47
    balleur
    0.47
    tdown
    0.46
    ↵
    0.45
    Act Density 0.419%

    No Known Activations