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

    Neuronpedia

    INDEX
    Explanations

    Subject command name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minutes
    0.47
     seconds
    0.44
     parties
    0.44
    haus
    0.43
    parties
    0.40
     minutos
    0.40
    annies
    0.39
     logged
    0.39
     colonies
    0.39
     housekeeping
    0.37
    POSITIVE LOGITS
     honing
    0.41
    هش
    0.39
     حول
    0.38
    ląd
    0.38
    污染
    0.37
    ieszcz
    0.37
    薨
    0.36
    ைகிறது
    0.35
    }^{*}\
    0.35
     Tartu
    0.35
    Act Density 0.000%

    No Known Activations