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

    Neuronpedia

    INDEX
    Explanations

    tailor to specific needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     majest
    0.46
     Buddhism
    0.43
     rotund
    0.41
     Buddhist
    0.39
     Buddhists
    0.39
    طلح
    0.38
     Pat
    0.38
    yfikacja
    0.38
     bulb
    0.38
    原因
    0.38
    POSITIVE LOGITS
     tailored
    1.26
     tailor
    1.21
     tailoring
    0.96
    针对
    0.83
     spécifique
    0.78
     específicas
    0.77
    定制
    0.76
     específicos
    0.76
     spezif
    0.75
     customized
    0.75
    Act Density 0.192%

    No Known Activations