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

    Neuronpedia

    INDEX
    Explanations

    of/for followed by another/invalid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.55
     pectoral
    0.53
     livre
    0.48
    ע
    0.47
     за
    0.46
    ه
    0.46
     pied
    0.45
    ţia
    0.45
    зи
    0.44
     которого
    0.44
    POSITIVE LOGITS
     Aware
    0.46
    grade
    0.46
     erhöht
    0.44
    orsk
    0.44
    aksha
    0.44
    )}>
    0.43
    gates
    0.43
    t
    0.43
    nYou
    0.42
    ാവ
    0.42
    Act Density 0.000%

    No Known Activations