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

    Neuronpedia

    INDEX
    Explanations

    social assistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <%@
    0.43
     exacting
    0.43
     सूफ़ी
    0.41
    㙅
    0.41
    orr
    0.40
     Ա
    0.40
     clears
    0.40
     montaje
    0.39
    掣
    0.38
    ualaikum
    0.38
    POSITIVE LOGITS
     Ear
    0.40
     Hearing
    0.38
     mismatch
    0.38
     hear
    0.38
     hearing
    0.37
    strom
    0.37
    好的
    0.37
    ('/').
    0.37
     decent
    0.36
    listener
    0.36
    Act Density 0.000%

    No Known Activations