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

    Neuronpedia

    INDEX
    Explanations

    because of the brave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unor
    0.35
    viamente
    0.31
     jaz
    0.31
     jaun
    0.31
    近期
    0.31
     opsi
    0.31
    )،
    0.30
     idiosyncratic
    0.30
     relativamente
    0.30
    تباين
    0.30
    POSITIVE LOGITS
     Leadership
    0.39
     Vishnu
    0.38
     Einstein
    0.36
     zuerst
    0.35
     Созда
    0.35
     tomorrow
    0.35
     Silence
    0.35
    äume
    0.35
     Thoreau
    0.34
     тільки
    0.34
    Act Density 0.083%

    No Known Activations