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

    Neuronpedia

    INDEX
    Explanations

    German language related to possibility

    oai_token-act-pair · gemini-2.0-flash

    war

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     was
    -2.48
    was
    -2.05
    Was
    -2.00
     Was
    -1.94
     were
    -1.93
     WAS
    -1.54
    were
    -1.46
    Were
    -1.45
     Were
    -1.42
     wasn
    -1.41
    POSITIVE LOGITS
     war
    0.67
    WAR
    0.66
    War
    0.62
    war
    0.59
     WAR
    0.55
     War
    0.52
     guerres
    0.49
     guerra
    0.47
    era
    0.44
     oamen
    0.44
    Act Density 1.052%

    No Known Activations