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

    Neuronpedia

    INDEX
    Explanations

    Distance Vector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ING
    0.54
    IKA
    0.53
     brengen
    0.50
    Hope
    0.48
    ارين
    0.47
    Explanation
    0.46
    ITO
    0.46
    ED
    0.46
    ENTY
    0.46
    DR
    0.46
    POSITIVE LOGITS
    ных
    0.55
    ’
    0.55
     встречается
    0.47
    
    0.47
     dilig
    0.46
    ómico
    0.46
     Americas
    0.46
     oficio
    0.45
     кораб
    0.45
     origem
    0.44
    Act Density 0.000%

    No Known Activations