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

    Neuronpedia

    INDEX
    Explanations

    start of week schedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ם
    2.85
     sted
    2.70
    党员
    2.68
     tornar
    2.68
    п
    2.66
    จะ
    2.66
    ehr
    2.64
    ів
    2.63
    ър
    2.62
     tornare
    2.60
    POSITIVE LOGITS
    harth
    3.13
    ق
    3.06
    ज
    2.96
    ുള്ള
    2.69
    сал
    2.69
    ංශ
    2.64
    शहर
    2.63
     skriv
    2.61
    ВА
    2.60
    Phương
    2.59
    Act Density 0.015%

    No Known Activations